探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12821

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models

作者:

Gabriel Diaz-Ireland↗Diego Prieto-Herr\'aez↗Mario Garc\'ia Peces↗Javier Vel\'azquez↗Devika Jain↗

arXiv:2606.12821v1 Announce Type: new Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recovery, ranking, comparison, multilingual understanding, habitat analysis, and task rejection. Tasks are evaluated against an open, self-hostable API serving three environmental indicators across Spain and Portugal via sixteen tools. We evaluate seven LLMs (Claude Sonnet 4, DeepSeek V3.2, GLM-5, Gemini 2.5 Pro, Qwen3-235B, GPT-OSS-120B, Llama 4 Scout) under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. We find: (1) Claude Sonnet 4 leads at 60.8% +/- 0.8%, followed by DeepSeek V3.2 at 56.3% +/- 3.1%, with no other model above 51%; (2) the cost-accuracy Pareto frontier is occupied mostly by open-weight models, with DeepSeek V3.2 offering 93% of Claude's capability at 11x lower cost ($0.011/case); (3) comparison tasks remain universally unsolved (0% on close-value comparisons), exposing systematic reasoning limits; and (4) structured tool calling against a real API is more discriminative than general-purpose GIS benchmarks, with accuracies 25-35 points lower. We further show extensibility by integrating BigEarthNet V2 land cover for Portugal alongside Spanish CO2 and erosion indicators. The benchmark, harness, and self-hostable API are publicly available.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19334

Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States

作者:

Denis Peskoff↗Joe Barrow↗Christopher Vu↗Diag Davenport↗

Progress in legal AI increasingly depends on access to authoritative legal text at scale. Yet one of the most consequential layers of American law remains largely absent from existing machine-readable corpora: local ordinances. Local codes govern zoning, housing, business licensing, public health, noise, animal control, and many other domains of everyday regulation, but they are fragmented across vendor platforms designed for human browsing rather than bulk research access. We introduce LOCUS - the Local Ordinance Corpus for the United States - a comprehensive corpus and county-harmonized access layer for U.S. municipal and county ordinance codes. The raw corpus, available for release to researchers, represents nearly all publicly available municipal and county ordinance codes. The resulting raw corpus contains codes from 9,239 cities and counties. A smaller county-harmonized LOCUS access layer provides coverage for the largest 2,309 of 3,144 U.S. counties, accounting for a majority of the population. We use OCR to handle the myriad of document formats that have kept the law from being a public resource. We release the corpus with coverage metadata to support reproducibility, downstream legal AI research, and the incremental expansion of machine-readable access to local law. We train a collection of ModernBERT-based classifiers and scorers to facilitate analyzing U.S. local law among several dimensions, such as opacity and paternalism, that have not previously been studied at this scale. LOCUS-v1 and its derivative models are available at: https://huggingface.co/datasets/LocalLaws/LOCUS-v1

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17113

The Critical Role of Model Selection in Causal Inference: A Comparative Analysis of Classification Models within the InferBERT Framework for Pharmacovigilance

作者:

Csaba Kiss↗Roland Molontay↗Gabriele Pergola↗

Distinguishing causal adverse drug events (ADEs) from spurious correlations remains a central challenge in pharmacovigilance. The InferBERT framework integrates transformer models with Do-calculus, but its success hinges on the underlying classification model. This study evaluates the impact of model choice in InferBERT, assessing whether simpler models suffice, if domain-specific pre-training helps, whether scaling to LLMs improves causal detection, and the effect of post-hoc calibration. We performed a comparative study on two benchmarks: Analgesics-induced Acute Liver Failure (AILF) and Tramadol-related Mortalities (TRAM). Four models were evaluated-XGBoost (baseline), ALBERT (original InferBERT), BioBERT (biomedical transformer), and Med-LLaMA (medical LLM)-using 5-fold cross-validation repeated over 20 runs. We measured accuracy, Expected Calibration Error (ECE) pre- and post-isotonic regression, and Jaccard concordance of causal terms with PRR, ROR, and EBGM; significance was tested with paired t-tests. BioBERT achieved the highest accuracy on both datasets, while Med-LLaMA underperformed despite its size and parameter-efficient fine-tuning. Domain-specific pre-training was decisive. Calibration improved ECE but had mixed effects on accuracy and causal discovery. BioBERT's superiority also yielded the strongest concordance with traditional pharmacovigilance signals. These results show that domain-specific pre-training provides a clear advantage over simpler baselines and larger LLMs. Investing in manageable, domain-aware models is more effective for computational pharmacovigilance than simply scaling model size.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18310

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

作者:

Xinru Liu↗Xianglong Zhang↗Di Cai↗Zhumin Chen↗Pengfei Hu↗Xin Xin↗

arXiv:2606.18310v1 Announce Type: cross Abstract: Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications. Existing RAG injection attacks mainly rely on manipulating external knowledge bases, such as crafting malicious corpus. However, the synthetic text crafted by such data-centric methods could be detectable, leading to the failure of attacks. Beyond corpus manipulation, open-source retrievers are increasingly exposing RAG systems to model-centric attacks. In this paper, we propose conflict-aware retriever editing, i.e., CAREATTACK, a model-centric retriever attack framework for malicious knowledge injection in RAG. Specifically, CAREATTACK consists two stages of conflict-aware retriever editing and attack-preserving anchor repair. Conflict-aware retriever editing adapts efficient closed-form parameter editing to the dense retrieval model, promoting malicious knowledge above benign competing passages and resolving potential parameter conflicts through graph-based conflict detection and parameter editing projection. Then, attack-preserving anchor repair performs lightweight calibration on the edited retriever to further eliminate the impact on non-target prompts while preserving the attack effectiveness for target prompts. We instantiate CAREATTACK on Qwen3-Embedding-0.6B and BGE-M3, and conduct evaluation on three benchmark datasets. Experimental results demonstrate our method substantially promote malicious passages into the retrieved knowledge of RAG systems and can perform attacks for batches of target prompts and passages, given the access of retrieval model parameters. Since most RAG systems are built upon open-source retrieval models, this work reveals a practical attack surface in RAG systems. Codes are public accessible at https://anonymous.4open.science/r/CareAttack-3F1C.

阅读与讨论 → 访问原文 →

05.

Nature (Science) 2026-06-08 DOI: HASH:9555f39dd9852bd80606705e171a8fe8

Distributed control circuits across a brain-and-cord connectome

作者:

Alexander S. Bates↗

Just as genomes revolutionized molecular genetics, connectomes (maps of neurons and synapses) are transforming neuroscience. To date, the only organisms with complete connectomes are worms1–3, sea squirts4, and comb jellies5 (103–104 synapses). By contrast, the fruit fly is more complex (108 synaptic connections), with a brain that supports learning and spatial memory6,7 and an intricate ventral nerve cord analogous to the vertebrate spinal cord8–12. Here we report the first densely-reconstructed adult fly connectome that unites the brain and ventral nerve cord, and we leverage this resource to investigate principles of neural control. We show that effector neurons (motor neurons, endocrine cells, and efferent neurons targeting the viscera) are primarily influenced by sensory neurons in the same body part, forming local feedback loops. These local loops are linked by long-range circuits involving ascending and descending neurons organized into behavior-centric modules. Single ascending and descending neurons are often positioned to influence the voluntary movements of multiple body parts, together with the endocrine cells or visceral organs that support those movements. Brain regions involved in learning and navigation supervise these circuits. These results reveal an architecture that is distributed, parallelized, and embodied, reminiscent of distributed control architectures in engineered systems13,14.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12125

Q-Fold: Query-Aware Focus-Context Spatio-Temporal Folding for Long Video Understanding

作者:

Biao Tang↗Xu Chen↗Shuxiang Gou↗Jingyi Yuan↗Yuhan Zhang↗Chenqiang Gao↗

Long-video understanding remains challenging for multimodal large language models, because temporally extended videos often contain thousands of frames and are therefore expensive to process exhaustively. Existing methods usually construct compact visual inputs from long videos under a limited visual budget. However, most of them still follow a frame-centric paradigm and apply similar representations to retained content regardless of its importance. This makes it difficult to preserve both high-fidelity visual evidence and broad temporal coverage. To address this issue, we propose Q-Fold, a training-free input construction framework for long-video understanding. Instead of treating isolated frames as the basic modeling unit, Q-Fold operates on contiguous temporal segments and constructs a heterogeneous Focus–Context representation under query guidance. Query-relevant segments are preserved as high-fidelity Focus Frames, while less relevant segments are folded into chronology-preserving contextual layouts. In this way, Q-Fold preserves critical visual evidence and broad temporal coverage, while better maintaining local temporal continuity within short segments. Experiments on four long-video benchmarks with multiple Video-MLLMs show that Q-Fold consistently improves performance without increasing the input budget. Notably, it achieves gains of up to 9.1 percentage points on an ultra-long video benchmark. Code will be made publicly available.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15974

A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization

作者:

Weixiao Zhou↗Gengyao Li↗Xianfu Cheng↗Junnan Zhu↗Feifei Zhai↗Zhoujun Li↗

Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths, and sample sizes. Furthermore, existing benchmarks often omit frontier reasoning systems and efficient small models, or lack fine-grained, multi-dimensional assessments. To bridge these gaps, we propose OmniCSEval, a unified benchmark comprising 1,800 diverse conversations across six real-world scenarios, featuring context lengths ranging from 128 to 32k tokens. For fine-grained evaluation, we employ a bidirectional fact-checking framework that integrates key fact matching to assess completeness and conciseness, alongside summary fact verification to evaluate faithfulness. To ensure reliable assessment, we establish a human-LLM collaborative pipeline for key fact extraction and a multi-LLM consensus verifier for summary fact decomposition. Leveraging this framework, we evaluate 28 LLMs across four distinct categories grouped by reasoning capability and model scale. Our extensive empirical study reveals critical insights regarding the cross-scenario challenges current LLMs continue to face, the impacts of reasoning and scale, and the efficiency and adaptability of reasoning models. We also provide guidance for system selection in real-world deployments.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.11190

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

作者:

Ilay Kamai↗Hugues Van Assel↗Aviv Regev↗Hagai B. Perets↗Randall Balestriero↗

arXiv:2606.11190v2 Announce Type: replace Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all – a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality. We develop a unified linear framework that addresses both questions. Under a spiked signal-plus-noise model with structured cross-modal nuisance correlation, we derive separation ratios for both objectives that expose complementary failure modes: alignment whitens each modality and fails when nuisance is strongly correlated across views; prediction encodes whatever is cross-predictable through a one-sided whitening, with recovery governed by source-modality quality. The resulting phase diagram partitions multimodal problems into four regimes: Both, CA only, CP only, and Neither. We present a data-driven procedure to locate real-world datasets in this diagram using a small labeled subsample, identifying the preferred objective and prediction direction before any cross-modal training. Experiments on synthetic data, stereo-vision benchmarks, image-caption pairs, and real astrophysical data validate the predictions in the nonlinear regime, including the Neither regime where cross-modal training is actively harmful. Our framework lets practitioners diagnose their multimodal problem and choose the right objective before committing to training. Code to reproduce the results is available at https://github.com/IlayMalinyak/mm_align_vs_pred.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18732

Low-Cost Neuromorphic Fall Detection Using Synthetic Event Data and Hybrid SNNs

作者:

Guillermo Rojas↗Gonzalo Soto↗Daniel Yunge↗

This work presents the development of hybrid models that integrate spiking neural networks (SNNs) with components of convolutional neural networks (CNNs) to learn from simulated event-based camera data (Dynamic Vision Sensor, DVS) generated from conventional smartphone videos. Aimed primarily at human fall detection, the approach leverages the energy efficiency and spatio-temporal processing capabilities of SNNs by converting video frames into event-based data. The proposed models are evaluated through simulations on multiple datasets, comparing their performance to that of traditional machine learning models. Results demonstrate significant gains in efficiency without sacrificing accuracy, underscoring the potential of combining SNNs and DVS technology for complex tasks in real-world environments.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18816

SwitchBraidNet: Quantisation-Aware Lightweight Architecture for Hybrid Brain-Computer Interface

作者:

Gourav Siddhad↗Yogesh Kumar Meena↗

arXiv:2606.18816v1 Announce Type: cross Abstract: Hybrid brain-computer interfaces (BCIs) that integrate motor imagery (MI) and steady-state visual evoked potentials (SSVEP) provide high-dimensional neural decoding but typically exceed the computational limits of embedded hardware. To address this, we propose SwitchBraidNet, a compact EEG classification architecture designed for low-power deployment. The model employs a dual-path temporal braid to extract multiscale oscillatory features, an adaptive squeeze-and-excitation spatial switch for electrode gating, and a log-variance readout layer for direct band-power encoding. Furthermore, through systematic quantisation-aware training on the OpenBMI dataset, we compared SwitchBraidNet against four established baselines across FP32, FP16, and INT8 precisions. Experimental results demonstrate superior efficiency and performance, achieving MI accuracy of 69.49% (FP16), SSVEP accuracy of 93.48% (FP32), and a hybrid information transfer rate of 64.82 bits/min (FP16). With an INT8 footprint of only 3.03 KB, SwitchBraidNet maintains high accuracy across varying numerical precisions, demonstrating its suitability for low-power embedded BCI deployment.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19356

Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol

作者:

Anantha Sharma↗

When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped. Current retry strategies treat both cases identically (try again and hope for the best), leaving human supervisors unable to tell whether a retry was warranted or whether the system should have halted instead. We introduce the Argent Signaling Protocol (ASP), a compact machine-readable header that accompanies every AI-generated response with structured quality signals: certainty (@C), grounding (@G), stochasticity (@S), and an assumption index that classifies the evidentiary basis of each claim. These signals enable a controller to distinguish repairable failures from containment failures and route each case differently. We evaluate ASP in two modes. In standalone mode, a 27-question document-grounded QA benchmark over the Array BioPharma/Ono license agreement compares baseline prompts against ASP-instrumented controller actions across three local GGUF models. On Qwen~(0.8B), ASP improves pass rate from 11.1% to 33.3% and mean term coverage from 36.7% to 65.4%; on Dobby~(8B), ASP produces 4 fail-to-pass recoveries, raising pass rate from 33.3% to 44.4%; on SmolLM3~(3B), ASP alternates between repair and containment per question. Aggregate improvement is meaningful (12/81 to 21/81 passes). In multi-agent mode, an ASP sidecar sits between a retrieval agent and a downstream decision agent; the sidecar blocks 100% of ungrounded upstream outputs from reaching the downstream agent (24/27 blocked, 0 ungrounded propagations).

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13316

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

作者:

Xucong Wang↗Ziyu Ma↗Yong Wang↗Shidong Yang↗Hailang Huang↗Renda Li↗Pengkun Wang↗Xiangxiang Chu↗

arXiv:2606.13316v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods often encourage unnecessarily long reasoning rollouts, which can degrade reasoning coherence and exhaust the available context budget. Existing approaches to long-context organization often depend on external mechanisms to organize rollouts, rather than enabling the model to manage its own reasoning trajectory. To address this limitation, we propose ReSum, a novel RLVR framework that enables LLMs to compress and organize their reasoning trajectories through self-summarization. Our pilot studies show that self-summarization stabilizes generation by lowering token-level entropy, and that introducing a ``summarization'' phrase can substantially mitigate errors propagated from an incorrect rollout prefix. Motivated by these findings, ReSum adopts a summarization-aware adaptive rollout mechanism that contrastively evaluates whether self-summarization benefits the ongoing reasoning process. Specifically, when the model spontaneously triggers self-summarization, ReSum masks the summarization phrase to create a contrastive branch; for non-summarization positions, it instead randomly injects the phrase to create a matched branch. We further design a summarization-aware advantage to enable finer-grained comparison between contrastive rollout trajectories. Extensive experiments show that ReSum improves performance at an average of 4\% while reducing rollout length by 18.6\%.

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2505.10530

Exploring Variational Entanglement Hamiltonians

作者:

Yanick S. Kind↗Benedikt Fauseweh↗

arXiv:2505.10530v3 Announce Type: replace Abstract: Recent advances in analog and digital quantum-simulation platforms have enabled exploration of the spectrum of entanglement Hamiltonians via variational algorithms. In this work we analyze the convergence properties of the variationally obtained solutions and compare them to numerically exact calculations in quantum critical systems. We demonstrate that interpreting the cost functional as an integral permits the deployment of iterative quadrature schemes, thereby reducing the required number of measurements by more than an order of magnitude even in the presence of noise. We further show that a modified ansatz captures deviations from the Bisognano-Wichmann form in lattice models, improves convergence, improves trainability and provides a cost-function-level diagnostic for quantum phase transitions. Finally, we establish that a low cost value does not by itself guarantee convergence in trace distance. Nevertheless, it faithfully reproduces degeneracies and spectral gaps, which are essential for applications to topological phases.

阅读与讨论 → 访问原文 →

14.

PLOS Medicine 2026-06-09 DOI: HASH:16faeed28171e77cd398c26de19708f2

Prediction of hospitalisation in young children with pneumonia in Malawi: A machine learning-based approach

作者:

Patrick Staunton↗

by Patrick Staunton, Mohammad Adib Makrooni, Master Chisale, Billy Nyambolo, Joseph Wu, Damien McCarthy, Mark Ledwidge, Yasir Bin Nisar, Chris Watson, Balwani Mbakaya, Cathal Seoighe, Joe Gallagher Background Globally, pneumonia remains the single biggest cause of mortality in children under 5 years of age. This study sought to train and test a prediction model for hospitalisation within 7 days after initial presentation in 2- to 59-month-old Malawian children with WHO-defined pneumonia in primary care and compare its performance to existing risk prediction models. Methods and findings BIOTOPE is a cohort study of children with pneumonia in a primary healthcare setting in Malawi. The training cohort involved nine primary care centres and the testing cohort involved two primary care centres in Northern Malawi. The training cohort was recruited between December 2022 and April 2023 while the testing cohort was recruited in 2016. Participants were consecutive children aged 2–59 months presenting with cough and/or difficulty breathing and who were diagnosed as WHO-defined pneumonia in primary care of any severity. The training cohort was used to train and validate a machine learning model with a prespecified primary outcome defined as hospitalisation and/or death within 7 days as the outcome. This model was then further evaluated in the testing cohort.Median age was 15 months (interquartile range 8−27) in the training and 17 months (interquartile range 9−29) in the external testing cohort (52.1% and 54.4% male, respectively). Hospitalisation occurred in 14.3% (294) of the training cohort and 12.1% (55) of the testing cohort. There was one death in the training cohort only. WHO danger signs were present in 17.6% (360) and 15.9% (70) of children in the training and testing cohorts, respectively. The optimal machine learning model achieved an area under the receiver operating characteristic and precision recall curves of 0.87 and 0.57, respectively, in the testing cohort outperforming existing risk prediction models; furthermore, this model produced an expected calibration error of 0.16 (a logistic regression model using severity status as the response variable and the log odds of the machine learning model’s calibrated probabilities produced an intercept estimate of −0.32 and a slope estimate of 1.13). Key limitations include the use of hospitalisation and/or death as a severity outcome, which may reflect health system factors rather than true disease severity, that mortality-based comparisons were not possible due to low mortality in these primary care cohorts, and that comparator tools were developed for hospital populations rather than primary care populations. Conclusion This machine learning score outperformed traditional pneumonia risk scores in predicting hospitalisation within 7 days in Malawian children presenting to primary care. Traditional pneumonia risk scores diminish in performance when externally applied to new datasets suggesting they may not generalise well beyond their original derivation settings. Mortality-related findings are not applicable as there was only one death in this cohort. Overall these findings support the potential of machine learning to meaningfully improve early identification of children at risk of severe pneumonia in low-resource primary care settings. Further external validation and clinical impact studies are needed to confirm these results.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11632

Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure

作者:

Jun He↗Deying Yu↗

arXiv:2606.11632v1 Announce Type: cross Abstract: Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms – such as identity and access management (IAM), policy engines, consensus protocols, and audit logs – either enforce static, context-unaware permissions or merely record actions post-execution. This paper introduces the Sovereign Assurance Boundary (SAB), a certificate-bound runtime admission layer for autonomous execution authority. SAB intercepts agent proposals at an assurance airlock, compiles them into typed execution contracts $C$, and binds these contracts to cryptographic evidence digests $H(E)$ and policy versions. The contracts are then routed through consequence-aware certification paths. Upon successful admission, the system emits a signed Sovereign Assurance Certificate ($\Omega$) that is strictly scoped to a specific execution identity, revocation epoch, and validity window. Finally, a sovereign execution broker verifies $\Omega$ and performs fresh pre-execution revocation and drift checks before invoking infrastructure APIs. We detail the airlock-broker architecture, formalize its admission and revocation invariants, and report preliminary feasibility measurements from a Go prototype evaluated over 2,500 admission attempts. Ultimately, this broker-enforced model prevents autonomous reasoning from directly mutating state, transforming delegated execution authority into a cryptographically verifiable, evidence-bound, revocable, and replayable runtime artifact.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19286

Correct Yourself, Keep My Trust: How Self-Correction and Social Connection Shape Credibility in Social Chatbots

作者:

Biswadeep Sen↗Yi-Chieh Lee↗

arXiv:2606.19286v1 Announce Type: cross Abstract: When social chatbots make mistakes, and they do, how they recover determines whether users trust them again. Social chatbots are increasingly integrated into everyday life, yet they remain prone to generating convincing but inaccurate information. The social connection they build with users makes such errors particularly consequential. We conducted a between-subjects experiment (N=120) comparing three error correction strategies: a webpage retraction, self-correction by the same social chatbot, and correction by an expert chatbot. Our results reveal two key findings. First, all three strategies corrected the error equally well, but only self-correction did so without damaging the chatbot's credibility: participants rated self-correcting chatbots significantly higher in both trustworthiness and perceived expertise than chatbots whose errors were corrected by external sources. Second, the strength of the user's social connection with the chatbot, measured through social attraction and self-disclosure, significantly predicted the magnitude of belief change, but only when the chatbot corrected itself. Outsourcing corrections to an external source severed this link entirely. These findings suggest that social chatbots should correct their own mistakes rather than outsource corrections, and that investing in social connection is a functional mechanism that amplifies correction effectiveness, not merely a design feature. We discuss implications for designing chatbots that maintain long-term credibility while effectively addressing their own errors.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11379

Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline

作者:

Jamie Bergen↗Sarit Kraus↗

arXiv:2606.11379v1 Announce Type: new Abstract: Pre-mediation, the preparatory phase preceding direct human negotiation, plays a critical role in achieving mutually beneficial agreements, yet is often omitted due to cost, time, and limited access to trained mediators. We introduce an automated mediator for human negotiation, implemented as a structured pipeline of LLM modules, that supports pre-mediation in integrative negotiation settings. The pipeline decomposes preparation into specialized modules for dialogue, preference prediction, response-level critique, and structured summarization, separating inference, generation, and evaluation to address limitations of monolithic single-prompt approaches. We use the term "agent" for each module following common LLM-systems terminology, but the components are not autonomous and do not interact peer-to-peer; outputs are passed forward in a fixed sequence. We evaluate the system in two controlled human-subject experiments comparing AI-based pre-mediation with professional human mediators in a multi-issue negotiation scenario. On short-term self-reported measures, the automated mediator achieves preparation outcomes broadly comparable to human mediators, including trust in the mediator and confidence in reaching mutually beneficial agreements, while achieving substantially lower error on the preference-inference task under our scenario and prompts (36% lower RMSE). A second study shows that targeted prompt refinements reduce excessive affirmation patterns from 36.6% to 16.8%, matching human mediator baselines. Our findings suggest that structured LLM pipelines can provide scalable, low-effort pre-mediation support broadly comparable to human mediators on short-term self-reported preparation outcomes. The pipeline's single-party design mirrors how human mediators run pre-mediation today and enables parallel deployment across all parties to a dispute, supporting scalability.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2508.05782

FineDialFact: A benchmark for Fine-grained Dialogue Fact Verification

作者:

Xiangyan Chen↗Yufeng Li↗Yujian Gan↗Arkaitz Zubiaga↗Matthew Purver↗

Large language models are known to produce hallucinations - factually incorrect or fabricated information - which poses significant challenges for many natural language processing applications, such as dialogue systems. As a result, detecting hallucinations has become a critical area of research. Current approaches to hallucination detection in dialogue systems primarily focus on verifying the factual consistency of generated responses. However, these responses often contain a mix of accurate, inaccurate or non-verifiable facts, making the use of a single factual label overly simplistic and coarse-grained. In this paper, we introduce a benchmark, FineDialFact, for fine-grained dialogue fact verification, which involves verifying atomic facts extracted from dialogue responses. To support this, we construct a dataset based on publicly available dialogue datasets and evaluate it using various baseline methods. Experimental results demonstrate that methods incorporating Chain-of-Thought reasoning can enhance performance in dialogue fact verification. Despite this, the best F1-score achieved on the HybriDialogue, an open-domain dialogue dataset, is only 0.74, indicating that the benchmark remains a challenging task for future research. We release our dataset and code at https://github.com/XiangyanChen/FineDialFact.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17819

A Framework for Evaluating Agentic Skills at Scale

作者:

Maksim Shaposhnikov↗Nicolas Fortuin↗Simon Stipcich↗Maria I. Gorinova↗Amy Heineike↗Rob Willoughby↗

Agent skills – structured, reusable knowledge artifacts that augment LLM agent capabilities – have been rapidly adopted in industry, yet their cross-domain impact and use across commercial and open-source models remain under-studied, and no reusable methodology exists for evaluating an individual skill. In this work, we present an evaluation framework that lets a skill author construct realistic tasks to rigorously assess the aspects of a skill that matter most to them, and that estimates skill utility by solving those tasks. Further, we apply our evaluation approach at scale to 500 real-world skills, generating 1,000 tasks derived from the skills' content, along with instruction-following and goal-completion scoring rubrics. Using these metrics, we evaluate how 19 agent-model configurations, both proprietary and open-source, perform on the tasks. Our results show that models vary widely in how closely they adhere to the instructions encoded in skills, leading to substantial differences in their performance gains. Furthermore, we show that access to a skill significantly changes model behavior compared to the no-skill setup, providing an essential mechanism for encoding opinionated workflows into LLM agents. We release our evaluation dataset to support future work on agent skills.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14702

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

作者:

Xinyue Cai↗Chaoyou Fu↗Yi-Fan Zhang↗Ran He↗Caifeng Shan↗

Current automated pipelines for audio-visual Question Answering (QA) generally adopt a ``video-caption-QA'' paradigm. However, these methods typically segment videos into short clips and generate separate descriptions for audio and visual modalities. This decoupled processing severs inherent associations between sounds and their visual sources, while independent clip processing often causes inconsistent descriptions of the same entity across segments. Furthermore, coupling long-text comprehension and QA synthesis into a single step often restricts models to localized events, yielding questions lacking long-term temporal connections and deep cross-modal reasoning. To address these issues, we propose an automated data engine featuring two mechanisms: (1) Entity-Anchored Video Scripting transforms videos into structured scripts, comprising summaries, main entity lists, and segment-wise audio-visual descriptions. The entity list serves as a global prior to ensure cross-segment referential consistency and reconstruct audio-visual associations. (2) Clue-Guided QA Generation prompts models to first mine cross-segment, multimodal clues from the script, and subsequently generate QA pairs based on these high-value clues. Leveraging this pipeline, we construct the instruction-tuning dataset OmniVideo-100K and a human-verified test set, OmniVideo-Test. Fine-tuning VITA-1.5, Qwen2.5-Omni-7B and Qwen3-Omni-30B on OmniVideo-100K yields performance gains of up to 20.59% on OmniVideo-Test, demonstrating strong generalization (up to 12.64% improvements) across established benchmarks like Daily-Omni and JointAVBench.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2605.24795

Lifted Schrödinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions

作者:

Siddhartha Ganguly↗George Rapakoulias↗Panagiotis Tsiotras↗

arXiv:2605.24795v2 Announce Type: replace-cross Abstract: We study stochastic density control between Gaussian-mixture endpoint distributions under Brownian prior dynamics. Since the direct Schrödinger bridge between Gaussian mixtures is generally not available in closed form, we introduce a lifted path-space construction in which each trajectory is augmented with a source–target component label. Consequently, the problem decomposes into Gaussian component-to-component Schrödinger bridges with explicit marginal, drift, and cost formulas, while the mixture-level assignment reduces to a finite-dimensional entropic coupling problem with a Sinkhorn scaling form. We then analyze the projection obtained by discarding or forgetting the label. By construction, the projected law satisfies the original Gaussian-mixture endpoint constraints, but its relative entropy generally differs from the lifted relative entropy by a nonnegative conditional label-information gap. This gap reveals a path-space obstruction: the lifted optimizer cannot, in general, be identified with the direct unlabeled Schrödinger bridge after projection. We also derive the posterior-averaged Markov drift associated with the projected marginal flow, prove a kinetic-energy upper bound, and identify a common path-potential condition under which the projection gap vanishes. Several numerical illustrations showing density and shape control are recorded for a self-contained exposition.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11639

Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models

作者:

Catherine Bao↗Maneesha Rani Saha↗Neal Patwari↗

The popularization of automatic speech recognition (ASR) systems has increased exploration of the demographic biases related to race, age, gender, and accent, often formed from imbalanced training data. Most of these studies focused on standard grapheme-based ASR systems with comparatively little emphasis on phoneme-based systems, such as models that produce International Phonetic Alphabet (IPA) representations. As ASR systems shift toward multilingual support and low-resource language modeling, IPA-based layers serve as a critical, language-agnostic foundation. In this study, we evaluate the performance of two state-of-the-art open-source ASR systems, WhisperIPA and ZIPA, that generate IPA transcriptions across diverse accents and language sources. Our evaluation includes existing multilingual speech corpora and demographically annotated English-language corpora. We measure model performance by comparing model-generated IPA transcriptions against grapheme-to-phoneme (G2P) systems using both standard phoneme error rate (PER) and a proposed Soft PER metric that tolerates linguistically similar phoneme substitutions. Our analysis examines how performance varies across languages and demographic groups such as gender, accent, ethnicity, and age, revealing persistent disparities even after accounting for acceptable phonemic variation. These findings provide insight into potential sources of bias and inform the development of more inclusive and linguistically robust phoneme-based ASR systems. Our code and data will be made publicly available to the community.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16993

DreamX-World 1.0: A General-Purpose Interactive World Model

作者:

DreamX Team↗Yancheng Bai↗Rui Chen↗Xiangxiang Chu↗Rujing Dang↗Hao Dou↗Bingjie Gao↗Qiwen Gu↗Siyu Hong↗Jiachen Lei↗Geng Li↗Jifan Li↗…

DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photorealistic, game-style, and stylized domains. Our data engine combines camera-accurate Unreal Engine rendering, action-rich gameplay recordings, and real-world videos with recovered camera geometry. For camera control, we introduce E-PRoPE, a lightweight variant of projective positional encoding that retains PRoPE's projective camera geometry while applying camera-aware attention to spatially reduced tokens. We convert a bidirectional video generator into a few-step autoregressive world model using causal forcing, DMD-style distillation, and long-rollout training. Training on self-generated long-horizon contexts exposes the model to its own generated history and reduces the style and color drift that accumulates across autoregressive chunks. Memory-Conditioned Scene Persistence retrieves earlier views through camera-geometry-based retrieval, while residual recycling makes the conditioning path less sensitive to imperfect memory latents. Event Instruction Tuning adds composable event control, and reinforcement learning alignment recovers camera control and visual quality after distillation. With mixed-precision DiT execution, residual reuse, 75\%-pruned VAE decoding, and asynchronous pipeline parallelism, DreamX-World 1.0 reaches up to 16\,FPS on eight RTX\,5090 GPUs. On our 5-second basic evaluation, DreamX-World 1.0 achieves a camera-control score of 73.75 and an overall score of 84.76, outperforming HY-WorldPlay 1.5 and LingBot-World in overall score, which achieve 80.79 and 80.45, respectively.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16032

Machine learning enables roughness-driven inverse design of milling processes

作者:

Hadi Bakhshan↗Sima Farshbaf↗Fernando Rastellini↗Josep Maria Carbonell↗

arXiv:2606.16032v1 Announce Type: cross Abstract: Interest in applying data-driven approaches in manufacturing has grown significantly, particularly for mapping complex, high-dimensional relationships. The milling process is one area where predictive models can link influential parameters to surface roughness metrics prior to in situ operations. While this approach offers clear advantages, it faces challenges due to limited datasets and robustness issues in inverse design paradigms. To address these challenges, this paper proposes a machine learning (ML)-based framework for the inverse design of the surface milling process, with a focus on surface roughness as the design objective. The framework employs forward training of two ML models, a deep neural network (DNN) and a random forest (RF) ensemble, both developed using a high-fidelity synthetic dataset generated from a computational simulation framework. These trained models are integrated into a Bayesian optimization (BO) procedure to overcome the multiplicity problem arising from the many-to-one mapping inherent in the dataset. The approach identifies top-performing milling process configurations, considering both process and tool parameters, and presents them from the full solution space. The models achieve average relative errors below 5% when compared to reference results, thereby demonstrating the robustness and reliability of the proposed methodology.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20545

Current World Models Lack a Persistent State Core

作者:

Jinpeng Lu↗Dexu Zhu↗Haoyuan Shi↗Linghan Cai↗Guo Tang↗Yinda Chen↗Jie Cao↗Duyu Tang↗Yi Zhang↗Yong Dai↗Xiaozhu Ju↗

World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on demand: it requires an internal world state that keeps evolving over time, decoupled from observation, so that objects endure and events run to their conclusions whether or not a camera is watching, much as the moon holds to its orbit when no one is looking. This requirement is a blind spot of existing benchmarks, which reward surface properties such as fidelity, motion, and camera controllability while never asking whether a generated world keeps evolving once it is unobserved. We introduce WRBench, the first systematic diagnostic benchmark that treats camera motion as an intervention on observability and resolves evaluation into a human-calibrated chain that asks whether the camera executes the requested interaction, whether the scene stays continuous and identifiable while in view, and whether a returning target remains consistent with the event that was set in motion. Across 9{,}600 videos from 23 models spanning four control paradigms, one finding proves stubborn: current systems maintain the observed world as a tracking shot, resuming a returning target in the state at which it was abandoned rather than advancing the event while it went unseen. Because this failure recurs across control paradigms, model families, and increments of scale, robust world-state evolution does not follow from cleaner imagery, tighter control, richer geometric priors, or sheer parameter count We therefore argue that the stability of the physical state kernel and the consistency of worldlines under viewpoint intervention should become first-class objectives of world-model design, so that a world model captures how the world will unfold rather than how the next frame appears.

阅读与讨论 → 访问原文 →