Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-16

Sleep regularity outweighs sleep duration as a predictor of disease

Sleep regularity, the consistency of sleep-wake timing from one day to the next, is more strongly associated with longevity than adequate sleep duration. Whether this relationship persists across common diseases is unknown. We compared sleep regularity vs. sleep duration as risk factors for 199 diseases and disorders, using ten million hours of objective sleep-wake data (N=60,998, age[mean{+/-}SD]=62.8{+/-}7.8, 55% female). Multivariable-adjusted risks of incident diseases/disorders for regular/irregular and short/adequate sleepers were compared across 9.5 years of follow-up. Irregular sleep predicted risks for 131 diseases/disorders, more than double the number predicted by short sleep duration (63). Irregular sleep was a superior predictor than short sleep duration for 90 diseases/disorders, including circulatory, metabolic, digestive, renal, infectious, neurological, and musculoskeletal conditions, and mental disorders, whereas short sleep duration was the superior predictor for only 9 diseases/disorders. For models where short sleep duration explained disease risks, 83% were improved by adding sleep regularity. Sleep regularity was a stronger predictor of diseases/disorders than sleep duration in this cohort and should be considered an essential dimension of sleep health.

02.
arXiv (CS.CV) 2026-06-19

TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living

Long Video Question Answering (LVQA) requires identifying sparse, query-relevant evidence within hours-long untrimmed videos. Existing approaches either process videos densely with large vision-language models (VLMs), incurring prohibitive computational cost, or rely on sparse caption-based reasoning, which often misses temporally localized and motion-centric evidence. We introduce TimeProVe, a cost-efficient hybrid framework for temporally grounded reasoning in long videos. TimeProVe first employs lightweight modules to generate action-grounded answer–evidence hypotheses and subsequently invokes an expensive VLM only for targeted verification. The core of our framework lies in the Action-based Candidate Evidence (ACE) module, which converts temporally localized actions into query-conditioned candidate answers and supporting evidence windows through lightweight LLM reasoning. We further introduce OpenTSUBench (OTB), an open-ended benchmark designed to evaluate temporally grounded reasoning in real-world Activities of Daily Living (ADL) scenarios. Experiments show that TimeProVe outperforms the strongest baseline on OTB by 7.3%, while reducing VLM calls by 75% and inference cost by 93%. Furthermore, without explicit temporal grounding training, TimeProVe achieves competitive performance on Charades-STA, and reaches state-of-the-art results when enhanced with grounding VLMs.

03.
arXiv (CS.CL) 2026-06-15

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks evaluate whether LLM-generated plans execute successfully, they overlook a critical type of failure: latent failures. Unlike immediate failures that trigger instant feedback at execution time and enable timely correction, latent failures do not immediately halt plan execution but silently compromise goal achievement. In severe cases, they cause irreversible harm. To address this gap, we introduce SIMMER, a benchmark for evaluating latent failures in LLM planning through a human-curated symbolic world model grounded in the kitchen domain. SIMMER defines a world model comprising 77 actions, 262 unique objects, and approximately 46,800 possible interactions that are semantically realistic, derived from real-world cooking scripts. It then leverages a state machine executor that validates plans against the world model and detects immediate precondition violations, latent hazards, and irreversible failures. Experiments across six LLMs show that even frontier models achieve at most 17% error-free plans. Moreover, up to 56% of plans contain latent failures, the majority of which lead to irreversible consequences. We further demonstrate that explicit state reasoning via counterfactual foresight simulation can reduce latent failures by up to 72% and irreversible cases by up to 75%, suggesting a promising direction for more robust LLM planners.

04.
arXiv (CS.CV) 2026-06-17

MagicSim: A Unified Infrastructure for Executable Embodied Interaction

Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment. Existing pipelines split these layers with "magic" actions, disconnected training environments, or forward-only renders that cannot reproduce, evaluate, and annotate the same episode. We present MagicSim, an embodied interaction infrastructure built around one deterministic batched runtime and a shared Markov decision process (MDP). From YAML-first specifications that decouple contents, placement, behavior, and agent exposure, MagicSim constructs diverse executable worlds spanning task families, interaction regimes, physics, layouts, sensors, avatars, and robot embodiments in one reset-and-step loop. A common execution interface grounds high-level commands through controllers, atomicskills, planner primitives, and asynchronous planning, realizing them as robot actions rather than simulator-side state edits. One task definition supports three capabilities: benchmark and RL evaluation, an autocollect interface that automatically turns commands into grounded trajectories, and agent/VLM-facing interaction. For automatic execution, commands flow through a Command->Skill->Planner->Robot->Record pipeline, while per-environment command, skill, planning, retry, annotation, and episode states advance independently above the shared physics tick. Successful rollouts are saved as structured multimodal trajectories aligning language supervision, action representations, visual/geometric representations, and task-level status with the executed episode. MagicSim thus unifies diverse world construction, embodied execution, task evaluation, automatic rollout generation, and interactive agent interfaces in one planner-in-the-loop runtime.

05.
arXiv (CS.CL) 2026-06-19

DeFrame: Debiasing Large Language Models Against Framing Effects

As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing – differences in how semantically equivalent prompts are expressed (e.g., "A is better than B" vs. "B is worse than A") – as an underexplored contributor to this gap. We first introduce the concept of "framing disparity" to quantify the impact of framing on fairness evaluation. By augmenting fairness evaluation benchmarks with alternative framings, we find that (1) fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged) fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses.

06.
arXiv (CS.AI) 2026-06-16

Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility

arXiv:2606.15251v1 Announce Type: cross Abstract: Accurate and interpretable motion prediction for heterogeneous traffic spaces, including pedestrians, bicycles, cars, and trucks, is essential for safe autonomous navigation. Nevertheless, state-of-the-art approaches remain predominantly black-box, lacking explicit encoding of the regulatory and behavioral constraints of real-world mobility. We propose Trajectory Compliance-Shaping (TraCS), a neuro-symbolic framework that augments existing black-box motion prediction backbones with interpretable and probabilistic first-order logic. To do so, TraCS employs an agentic code-generation pipeline to bridge the gap between natural-language descriptions of traffic regulations and probabilistic motion prediction. Furthermore, TraCS employs a reactive data-streaming inference engine that maintains and efficiently updates compliance landscapes as scenes evolve. To prevent TraCS from overconfidently steering the backbone's predictions in the wrong direction, we propose a neural confidence rating learned as a context-aware attenuation of the compliance signal. We demonstrate on the Argoverse 2 benchmark how TraCS consistently improves state-of-the-art prediction backbones, showing that probabilistic and symbolic compliance reasoning is a broadly applicable and computationally efficient complement to purely neural motion predictors.

07.
arXiv (CS.CV) 2026-06-17

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

08.
arXiv (quant-ph) 2026-06-15

Dynamically frozen long-distance entanglement via non-Hermitian PT-symmetric systems

arXiv:2606.14177v1 Announce Type: new Abstract: In distributed quantum networks, interacting spin systems can mediate the generation of highly entangled links between distant nodes. We investigate the role of effective parity-time (PT)-symmetric non-Hermitian spin-1/2 bulks weakly coupled to two quantum links, obtained due to the environmental interactions affecting both the bulk and the links. Focusing on effective non-Hermitian nearest-neighbor (NN) Su-Schrieffer-Heeger (SSH) models, we analyze how non-Hermiticity influences the dynamical formation of long-distance entanglement (LDE). For a paradigmatic model consisting of a quantum XX bulk subjected to imaginary staggered magnetic fields, we analytically determine the exceptional points arising from the resulting bulk-mediated interactions between the links. Combining analytical and numerical methods, we demonstrate that an initially fully separable state can dynamically evolve into highly entangled link states near these exceptional points in the broken regime. Further, after optimizing over time and system parameters, near-unit time-averaged entanglement between the links emerges under weak imaginary magnetic fields and bulk-link couplings, which cannot be attained in the corresponding Hermitian systems. Moreover, the non-Hermitian dynamics exhibit a freezing of high entanglement in the vicinity of exceptional points, a feature absent in Hermitian counterparts. We also identify regimes of long-range interaction strengths that yield a higher time-averaged entanglement than the corresponding NN models. Furthermore, we establish that LDE persists in the stationary regime, highlighting the promise of engineered non-Hermitian dynamics for realizing robust and frozen entangled links in quantum networks.

09.
arXiv (quant-ph) 2026-06-15

Extending Covariant Fluctuation Theorems into Quantum Regime through Quasiprobability Approach

arXiv:2606.14519v1 Announce Type: cross Abstract: The covariant formulation of stochastic thermodynamics requires treating the stochastic work as a 4-vector, posing significant challenges for quantum systems due to the non-commutativity. We introduce a new quasiprobability distribution for the work 4-vector, which combines the Wigner and Margenau-Hill quasiprobabilities. This extends the covariant fluctuation theorems from classical to quantum regime. We illustrate our findings with a scalar field driven by classical particles with a generalized version of trace formula. Our work establishes a quasiprobability approach to studying relativistic quantum thermodynamics in a covariant way.

10.
bioRxiv (Bioinfo) 2026-06-11

A multi-agent system for spine MRI report generation from multi-sequence imaging

Spinal pathology is a leading cause of pain and disability worldwide. Spine magnetic resonance imaging (MRI) is central to clinical evaluation, yet its interpretation remains complex and time-consuming, requiring integration of information across multiple imaging sequences and anatomical regions. Despite recent advances in automated MRI analysis, effectively combining multi-sequence data while preserving sequence-specific diagnostic information remains an open challenge. Here we present SpineAgent, a multi-agent framework for spine MRI report generation built upon a multi-sequence foundation model trained on routine clinical data from 32,047 patients and 453,683 MRI series, comprising a total of 13,441,191 MRI slices. To accommodate diverse modalities of sequences, we first pre-train two DINOv3-based encoders separately on T1- and T2-weighted sequences. We then introduce a continual training strategy that learns a synthesizer to embed images of other sequences using the T1 and T2 encoders, producing patient-level embedding that integrates various signals across MRI sequences. Using these embeddings, SpineAgent achieves state-of-the-art performance, with mean 10.8% AUROC improvement across 17 spinal condition-prediction tasks compared to the best competing method, and demonstrates strong generalizability under cross-manufacturer and cross-cohort evaluation. Beyond classification, SpineAgent enables pathology localization by identifying findings-relevant slices and segmenting pathological regions. It also supports multimodal image-report retrieval, providing a solid foundation for scalable and explainable MRI report generation. We further integrate these validated capabilities of SpineAgent into 37 specialized agents for condition diagnosis, pathological-region localization, and clinically-similar-cases retrieval. Finally, we incorporate their outputs as structured tokens within a Medical Report Agent trained end-to-end for report generation. Through both automated metrics and expert evaluation by five radiologists, SpineAgent achieves leading performance in spine MRI report generation. Together, SpineAgent introduces a continual training approach for multi-sequence spine MRI understanding. By decomposing report generation into clinically grounded subtasks addressed by specialized agents, the SpineAgent framework enables accurate, interpretable and generalizable spine MRI reporting across diverse imaging sequences and anatomical regions.

11.
arXiv (CS.AI) 2026-06-18

CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework

arXiv:2606.18385v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only partially address this, as they neither enforce step-level citation grounding nor route verification failures back to retrieval for correction. We present CaVe-VLM-CoT, a modular reflection-based agentic-RAG framework that enforces evidence-grounded reasoning through a five-stage closed-loop pipeline: Extractor, Retriever, Solver, Citation Injector, and Verifier, in which detected ungrounded claims trigger structured feedback to the Extractor for targeted re-retrieval. Since no existing framework jointly measures retrieval quality, step-wise citation faithfulness, and cross-modal grounding, we propose a suite of 23 component-wise metrics across all stages, anchored by CaVeScore, a composite metric weighting accuracy, citation precision and recall, attribution, and evidence grounding. Without any architectural or prompt modifications, CaVe-VLM-CoT achieves 87.1\% accuracy and 56.6\% CaVeScore on ScienceQA , and 55.2\% accuracy and 35.7\% CaVeScore on MMMU (30 subjects).

12.
medRxiv (Medicine) 2026-06-18

Avidity of anti-pertussis toxin antibodies is associated with symptomatic Bordetella pertussis infection in a novel controlled human infection model

Background The association between functional antibody responses following Bordetella pertussis infection and symptomatic disease remains unclear. We characterized the maturation of anti-pertussis toxin (PT) IgG avidity after human challenge with B. pertussis and determined its association with symptomatic infection. Methods Healthy adults were intranasally inoculated with live B. pertussis organisms in a controlled human infection model and monitored for development of pertussis symptoms (NCT05136599). Serum samples were collected one day before inoculation and at 14, 28, 56, 180, and 365 days post challenge. Anti PT IgG avidity was tested using a titration of ammonium isothiocyanate (the bond breaking agent) to quantify a wide range of antibody avidities from low to very-high. Associations between covariates and avidity were examined using linear regression models, and high dimensional analyses were used to integrate all data. Findings Anti PT IgG avidity increased in both symptomatic (n=20) and asymptomatic (n=10) participants after the challenge, reached maximum levels at day 56, and then declined through day 365. Symptomatic participants developed significantly higher levels of high- and very high-avidity anti-PT antibodies at 28, 56, 180, and 365 days post-challenge compared with those who remained asymptomatic. In multivariate analyses, symptomatic infection was associated with higher levels of high and very high avidity anti-PT IgG at day180 and365 after challenge. Distinct avidity profiles in symptomatic vs asymptomatic participants emerged at day28 onwards, with the former group having higher levels of antibodies with higher avidities. However, levels of medium-high, high and very high avidity antibodies in symptomatic participants were lower at day 365 after challenge compared to their peak levels. Interpretation Anti-PT IgG avidity was associated with symptomatic B. pertussis infection and thus may serve as a surrogate of clinical disease outcome. These results highlight that antibody avidity provides an additional functional assay besides antibody quantitation to dissect immune responses to pertussis. Further investigation of anti PT IgG avidity should be pursued in natural pertussis outbreaks to determine whether it might be used to differentiate symptomatic from asymptomatic infections for epidemiologic purposes.

13.
medRxiv (Medicine) 2026-06-15

Quality Improvement Based Implementation and Evaluation of a Decision Aid for Patients with Nephrolithiasis

Introduction Patients with nephrolithiasis face challenges in making a high-quality, preference sensitive decision. Our prior work established feasibility and patient acceptance of a software-based decision aid (DA). The objectives for this study were to identify implementation strategies for the DA in routine care and determine whether DA implementation enhances decisional quality for patients. Methods New nephrolithiasis patients were recruited from the institution Medical Center from June 2018 to April 2024 to receive a software-based pre-visit DA that measured care preferences and used decision analysis to rank treatments. The RE-AIM framework and Plan-Do-Study-Act (PDSA) cycles were used to improve implementation outcomes. Patients completed survey instruments evaluating decisional conflict, shared decision-making, care satisfaction, and treatment choice following their provider visit. These metrics were compared in the DA cohort (n=81) to those in a usual care cohort (n=78) with Wilcoxon rank-sum and Chi-square (or Fishers exact) tests. Results Implementation data revealed sustained reach and progressive improvement in fidelity. The DA cohort reported higher decisional quality relative to controls (p=0.003) and reported greater support/advice to make a choice (p=0.005). The DA cohort more often discussed options with their doctor (87.5% vs 69.2%, p=0.005) and were more likely to be promoters of their provider (p

14.
arXiv (CS.CV) 2026-06-16

Graph Regularized Non-negative Reduced Biquaternion Matrix Factorization for Color Image Recognition

Non-negative reduced biquaternion matrix factorization (NRBMF) uses the product of reduced biquaternion (RB) matrices to incorporate the non-negativity constraints of color image pixels into the factorization process. However, NRBMF mainly focuses on reconstruction accuracy and does not explicitly exploit the local geometric structure of image data, which may limit the discriminative ability of the obtained low-dimensional coefficient representations. To address this issue, we propose a graph regularized non-negative reduced biquaternion matrix factorization (GNRBMF) model for color image recognition. The proposed model incorporates a graph Laplacian regularizer into the reduced biquaternion coefficient matrix, encouraging nearby samples in the original space to have similar coefficient representations. Meanwhile, GNRBMF retains the non-negativity property of NRBMF in the reduced biquaternion algebra. To solve the optimization problem, a component-wise alternating projected gradient algorithm is derived, and its convergence properties are analyzed. Experimental results on three color image datasets show that the proposed GNRBMF model achieves competitive or superior recognition performance compared with several methods in most tested settings.

15.
arXiv (CS.AI) 2026-06-19

Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices

arXiv:2606.19528v1 Announce Type: cross Abstract: Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

16.
arXiv (CS.LG) 2026-06-12

Physics-Informed Neural Networks and Radial Basis Functions for PDEs with Dirac Delta Sources

arXiv:2606.12735v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) are a machine learning method for solving forward and inverse Partial Differential Equations (PDEs). When applied to PDEs with Dirac delta functions in the forcing terms, boundary conditions, or initial conditions, PINNs require approximating them with smooth surrogate functions, a practice that can introduce significant modeling errors. In this work, we exploit the interpretation of PINNs as Residual Least Squares (RLS) methods and show that this perspective enables direct treatment of Dirac delta terms by integrating the weak-form equation. Among RLS formulations other than PINN, we focus on the Radial Basis Function (RBF) expansion (also known as a single-layer RBF Network). We show that while integrating out the Dirac delta in PINNs causes residuals to fail to converge to zero, RBF-RLS consistently provides good forward and inverse solutions to transport problems. We explain this finding using the Neural Tangent Kernel (NTK) theory. We test both approaches on linear PDEs that represent groundwater flow and transport in porous media and rivers. We solve inverse problems to fit synthetic data, noisy synthetic data, and real-world measurements.

17.
arXiv (CS.CL) 2026-06-12

An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect

The rapid growth of social media has intensified the spread of rumours. This issue is more challenging in the Algerian context due to the informal and code-switched nature of dialectal content, the scarcity of annotated resources, and the limited effectiveness of standard Arabic NLP tools on dialect text. This paper presents an end-to-end rumour detection hybrid framework for Algerian dialect social media content. We build a domain-specific annotated dataset by combining real social media posts, synthetic data, and the FASSILA corpus, with automatic labeling based on a similarity-based annotation process. A transliteration pipeline is also introduced to generate parallel datasets in Arabic script and Arabizi. We evaluate multiple approaches, including classical machine learning, deep learning, transformers, and hybrid models. Experimental results show that a hybrid approach combining transformer embeddings with a classical classifier achieves the best performance, reaching an F1-score of 0.84. We also find that domain-specific pre-training is more important than model size, with social media-trained models outperforming larger models trained on formal Arabic corpora. These results demonstrate the feasibility of rumour detection in low-resource Algerian dialect settings.

18.
medRxiv (Medicine) 2026-06-22

A blinded, counterbalanced rater design for evaluating AI-assisted summarisation of tertiary clinical genomics reports: methodology of the QNOMX-VHIR-CPSP-001 Phase 1 study

Background. Tertiary clinical genomics reports condense layered molecular findings into documents that treating oncologists must read, translate, and act upon; manual summarisation of these reports is time-consuming and variable. Tools that assist summarisation and translation into local languages are emerging, yet the field lacks an agreed methodology for evaluating such tools before any downstream clinical use. The appropriate first endpoint is fidelity of the generated summary to its source report, assessed by qualified human raters under blinded scoring, not downstream variant classification. Methods. QNOMX-VHIR-CPSP-001 Phase 1 is a single-site, non-interventional clinical performance study conducted at Vall d'Hebron Institut de Recerca (VHIR) under ISO 20916:2019 as a Clinical Performance Study Protocol. De-identified tertiary cancer genomics reports from pediatric oncology cases are summarised by the AI-assisted summarisation system under evaluation and, in parallel, by the standard manual workflow. Qualified raters score both summary types against the source genomics report using the Quality Summary Index (QSI), a six-dimension, five-point rubric adapted from the Provider Documentation Summarization Quality Instrument, under a blinded, counterbalanced, two-period crossover with a minimum fourteen-day washout. Two co-primary composite endpoints, content and presentation, are analysed for non-inferiority under a Bayesian hierarchical model, with a frequentist linear mixed model as the convergence check. Inter-rater reliability is reported as Krippendorff's ; a Monte-Carlo power analysis of the fixed clustered design is pre-specified. Discussion. The design isolates summarisation quality from clinical decision-making by scoring both summary types against the same source report under blinding, counterbalancing, and a fourteen-day washout. Conclusion. The QSI rubric, the counterbalanced crossover, and the pre-specified Bayesian primary with frequentist convergence check define a replicable protocol for early-stage evaluation of AI-assisted summarisation in tertiary genomics reporting; observed variance components will inform sample-size determination for Phase 2.

19.
arXiv (CS.AI) 2026-06-17

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

arXiv:2606.18023v1 Announce Type: cross Abstract: Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count. Parallel loop Transformers (PLT) alleviate this cost through cross-loop position offsets (CLP) and shared-KV gated sliding-window attention, making loop count a practical design choice. We therefore study PLT loop-count selection through a gain–cost view: an extra loop may refine representations, but CLP also introduces a positional mismatch at each loop boundary. We instantiate this study by training LoopCoder-v2, a family of 7B PLT coders with different loop counts, from scratch on 18T tokens, followed by matched instruction tuning and evaluation. Empirically, the two-loop variant delivers broad gains over the non-looped baseline across code generation, code reasoning, agentic software engineering, and tool-use benchmarks, improving SWE-bench Verified from 43.0 to 64.4 points and Multi-SWE from 14.0 to 31.0 points. In contrast, variants with three or more loops regress, revealing a strongly non-monotonic loop-count effect. Our diagnostics show that loop 2 provides the main productive refinement, while later loops yield diminishing, oscillatory updates and reduced representational diversity. Because the CLP-induced mismatch remains roughly fixed as refinement gains shrink, the offset cost increasingly dominates. This gain–cost trade-off explains PLT's saturation at two loops and provides diagnostics for loop-count selection.

20.
arXiv (CS.AI) 2026-06-16

AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits in LLM Agents

arXiv:2606.15057v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work have proposed a variety of defensive approaches against IPI. These can be grouped into three broad categories: 1) prompt-based (using prompting as a way to prevent agents from following malicious instructions), 2) detection-based (identifying and filtering malicious instructions), and 3) system-level (using systems insights, such as control and data isolation, for defense). However, commonly used benchmarks for evaluating defense, such as AgentDojo, are inherently static, generating a fixed distribution of IPI attacks. Consequently, static benchmarks do not usefully evaluate defense robustness to adaptive threats. We address this issue by developing AutoDojo, an adaptive extension of AgentDojo that optimizes IPI against a given defense. Using AutoDojo against state-of-the-art IPI defenses across three task suites and five target models, we make two key observations. First, many defenses offer only limited protection: a cheap, black-box adaptive attack using a frontier LLM to iteratively optimize the injection raises attack success rate (ASR) well above the level achieved by static injections against nearly all evaluated defenses. Against a filter that reduces static ASR to 0\%, AutoDojo recovers 28\% overall and 64\% on action-open tasks. Second, for prompt-level and filter-based defenses, ASR is substantially higher on action-open tasks – where the user's request delegates the action itself to attacker-controlled content – than on precisely specified tasks. This is a structural limit: on such tasks the injection can pose as ordinary data rather than an explicit instruction, bypassing defenses that rely on detecting instruction-like text. AutoDojo is publicly available at https://github.com/xhOwenMa/AutoDojo.

21.
arXiv (CS.AI) 2026-06-12

Can I Buy Your KV Cache?

arXiv:2606.13361v1 Announce Type: new Abstract: Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

22.
arXiv (CS.AI) 2026-06-16

Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation

arXiv:2502.11201v3 Announce Type: replace-cross Abstract: NoSQL databases are core data infrastructure, yet natural-language access to them remains underdeveloped: correct query generation must recover how a non-relational data model represents entities, nested paths, arrays, missing fields, and dynamic keys. This paper studies Text-to-NoSQL, translating natural-language requests into executable NoSQL queries, instantiated with MongoDB aggregation pipelines over schema-less document stores. We present TEND, short for Text-to-NoSQL Dataset, an execution-verified benchmark with 1,210 MongoDB-native tasks across 11 databases. To our knowledge, TEND is the first Text-to-NoSQL benchmark whose database worlds are MongoDB-native by design: experts manually define collection boundaries, nested arrays, optional and sparse paths, polymorphic shapes, and dynamic-key conventions; these worlds are populated with real data and verified through frozen MongoDB execution, so TEND evaluates schema-less document reasoning rather than SQL-to-MQL transfer. We further introduce SAG, a Schema-as-Data Grounding solver that induces path and value grounding from stored-document evidence before bounded MQL generation, execution-grounded repair, and result-consistency selection. Evaluation uses bounded column-tolerant execution accuracy (EXC) as the headline metric, complemented by a graded result-set F1 and a mutually exclusive execution-outcome decomposition. Experiments show that LLMs with strong NL2SQL performance degrade substantially on TEND, validating Text-to-NoSQL as a distinct schema-less document reasoning problem.

23.
arXiv (CS.CL) 2026-06-16

It's About Time: Temporal References in Emergent Communication

Emergent communication enables agents to develop bespoke languages that improve communication efficiency. Despite the known importance of temporal structure in natural language, there is no existing evidence of temporal references in emergent communication. This paper addresses this gap, by exploring how agents communicate about temporal relationships. We analyse three potential factors for the emergence of temporal references: environmental, external, and architectural. Our experiments demonstrate that altering the loss function is insufficient for temporal references to emerge; rather, architectural changes are necessary. A minimal change in agent architecture, using a different batching method, allows the emergence of temporal references. This modified design is compared with the standard architecture in a temporal referential games environment, which emphasises temporal relationships. The analysis shows that over 95% of the agents with the modified batching method develop temporal references, without changes to their loss function. We consider temporal referencing necessary for future improvements to the agents' communication efficiency, enabling future agents to use a closer to optimal coding as compared to purely compositional languages. These insights provide the basis for incorporation of temporal references into other emergent communication settings, and investigation of other aspects of language.

24.
arXiv (CS.CV) 2026-06-18

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations. We take a different approach. Our method, ScenA, conditions a text-to-audio flow-matching foundation model, pretrained on large-scale in-the-wild data, directly on multiple reference voices and a free-form natural language prompt that describes an entire multi-speaker audio scene. Leveraging such a foundational model allows us to inherit its capacity for natural, non-studio audio: background noise, room acoustics, overlapping dialogue, and spontaneous paralinguistic events, while adding multi-speaker control without any per-turn structure. Concretely, reference latents are concatenated into the model's token sequence and distinguished by lightweight identity-aware positional encodings. However, we identify a critical obstacle to this approach: the Reference Shortcut. During training under standard noise schedules, the model can identify the matching reference by acoustic similarity to the noisy target, bypassing the text prompt entirely. We address this with a high-noise-biased timestep distribution that forces the model to rely on the text prompt for speaker assignment. We evaluate ScenA on the CoVoMix2-Dialogue benchmark, showing that it outperforms existing multi-speaker systems on speaker-binding metrics while generating rich conversational audio with overlapping speech, emotional vocalizations, and ambient sound. Our results demonstrate the advantage of using a general-purpose audio model conditioned on a free-form scene description, rather than passing structured dialog scripts through a speech-only pipeline.

25.
arXiv (CS.CV) 2026-06-16

Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT

Human perception of visual scenes is inherently temporal. We instinctively recognise whether a fruit is ripening or rotting, whether construction is progressing or being demolished, and approximately how much time separates two photographs of the same subject. Whether large vision-language models (VLMs) share this competence remains an open and practically important question. We introduce CHRONOSIGHT, a rigorously controlled benchmark evaluating five dimensions of visual temporal reasoning: CHRONORANK (chronological ordering of image sequences), CHRONOLOCATE (ordinal stage localisation from a single image), CHRONODELTA (estimation of time elapsed between two images on a logarithmic scale), CHRONOREVERSE (detection of temporally reversed sequences), and CHRONOODD (identification of a temporal outlier within a set). The benchmark comprises 1{,}000 items across eight process families (biological growth, food transformation, physical weathering, construction, environmental change, human ageing, astronomical phenomena, and urban dynamics) spanning timescales from minutes to millennia. We evaluate eight open-source VLMs (500 M to 19 B parameters) under two prompting regimes and collect human performance baselines. Human performance averages 0.89 across tasks; the best open model (Qwen2.5-VL-7B) reaches 0.40 under direct prompting, a gap we term chronological blindness. Lightweight LoRA fine-tuning on 151 examples raises CHRONODELTA accuracy from near-zero to 0.43, transferring zero-shot to related tasks (CHRONOODD: 0.37; CHRONOREVERSE: 0.64)suggesting the bottleneck is partly instruction following rather than visual perception. Benchmark, code, and predictions will be released upon acceptance.