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.
arXiv (CS.CV) 2026-06-15

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative backbones. The emergence of representation autoencoders (RAEs) shifts the generation target toward semantically structured visual representations, creating a latent space that is more compatible with pretrained LLM priors. Inspired by multimodal LLMs (MLLMs), where an MLP projector is sufficient to align clean visual representations with a pretrained LLM, we repurpose the MLLM itself as a noisy representation encoder, extending this mechanism from clean to noisy inputs. We present RepFusion, which uses the resulting MLLM outputs as the conditioning signal for a diffusion transformer. In controlled comparisons at similar inference budgets, RepFusion outperforms baselines that devote comparable capacity to newly initialized denoisers. These results demonstrate that MLLMs provide strong priors for denoising visual representations and that, by conditioning on evolving noisy representations, test-time compute can be productively spent on repeated MLLM conditioning in modern T2I systems.

02.
arXiv (CS.LG) 2026-06-11

TacCoRL: Integrating Tactile Feedback into VLA via Simulation

arXiv:2606.11743v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks. We present TacCoRL, a scalable framework that injects Tactile feedback into VLA policies and improves them through sim-real Co-training and simulation-based reinforcement learning (RL), without requiring large-scale tactile pretraining or extensive real-world contact exploration. The key idea is not only adding touch as an input, but learning how contact readings should modulate action responses in near-failure states that are rare in demonstrations and risky to collect on hardware. We use a real-aligned simulator as a closed-loop training environment for contact interaction. Mixed simulated and real trajectories first warm-start tactile-conditioned actions in the pretrained policy. Reinforcement learning with verifiable task rewards then optimizes the policy using simulated contact rollouts. It reinforces tactile-conditioned actions that lead to task completion, while a supervised objective on real trajectories keeps the refined policy anchored to deployment visual, tactile, and action distributions. The resulting policy transfers directly to the real robot without privileged simulation state or online real-world RL. Across four bimanual contact-rich tasks, the final visuo-tactile policy achieves an average success rate of 72.5%, compared to baseline of 50.0%. Result videos and more details are available at https://tac-corl.github.io/

03.
arXiv (quant-ph) 2026-06-12

The Pound-Drever-Hall Method for Superconducting-Qubit Readout

arXiv:2512.03138v3 Announce Type: replace Abstract: Scaling quantum computers to large sizes requires the implementation of many parallel qubit readouts. Here we present an ultrastable superconducting-qubit readout method using the multi-tone self-phase-referenced Pound-Drever-Hall (PDH) technique, originally developed for use with optical cavities. In this work, we benchmark PDH readout of a single transmon qubit, using room-temperature heterodyne detection of all tones to reconstruct the PDH signal. We demonstrate that PDH qubit readout is insensitive to microwave phase drift, displaying $0.73^\circ$ phase stability over 2 hours, and capable of single-shot readout in the presence of phase errors exceeding the phase shift induced by the qubit state. We show that the PDH sideband tones do not cause unwanted measurement-induced state transitions for a transmon qubit, leading to a potential signal enhancement of at least $14$~dB.

04.
arXiv (CS.CL) 2026-06-12

PolyAlign: Conditional Human-Distribution Alignment

Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective for improving average helpfulness, this can suppress the natural variation of human responses across languages, tasks, and dialogue settings. We study this problem as conditional human-distribution alignment: models should match the human response distribution appropriate to the current interaction context, rather than a universal response style. We introduce PolyAlign, a distribution-aware alignment framework that organizes bilingual interaction data into bucket-specific human reference distributions defined by language, interaction track, response family, and length. PolyAlign combines Bucket-Aware SFT, which balances optimization across heterogeneous buckets, with Human-Distribution Preference Optimization (HDPO), which regularizes preference learning using critic-estimated distance to bucket-specific human support. Across a bilingual evaluation suite covering English and Chinese single- and multi-turn settings, PolyAlign improves conditional naturalness and distributional faithfulness while preserving competitive task utility. The results suggest that post-training should move beyond global alignment objectives toward interaction-aware alignment with human response distributions.

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

Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades

We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downstream semantic failures that conventional ASR metrics cannot fully capture. Our analysis shows that the relative downstream degradation caused by ASR errors is consistent across LLMs with different absolute performance, suggesting that cascade degradation largely tracks ASR-stage information loss. We further identify single-character Korean ASR errors as a Korean-specific loss channel, where even a minimal transcription difference can change the intended question and degrade downstream QA performance. Finally, an auxiliary comparison shows that a large audio language model outperforms an ASR-LLM cascade with an approximately matched language backbone in noisy Korean SQA, indicating the potential of direct audio input to mitigate transcript-induced information loss.

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

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

07.
arXiv (CS.CV) 2026-06-16

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change captioning datasets typically describe overall image-level differences, leaving fine-grained localized semantic reasoning largely unexplored. To close this gap, we present RSRCC, a new benchmark for remote sensing change question-answering containing 126k questions, split into 87k training, 17.1k validation, and 22k test instances. Unlike prior datasets, RSRCC is built around localized, change-specific questions that require reasoning about a particular semantic change. To the best of our knowledge, this is the first remote sensing change question-answering benchmark designed explicitly for such fine-grained reasoning-based supervision. To construct RSRCC, we introduce a hierarchical semi-supervised curation pipeline that uses Best-of-N ranking as a critical final ambiguity-resolution stage. First, candidate change regions are extracted from semantic segmentation masks, then initially screened using an image-text embedding model, and finally validated through retrieval-augmented vision-language curation with Best-of-N ranking. This process enables scalable filtering of noisy and ambiguous candidates while preserving semantically meaningful changes. The dataset is available at https://huggingface.co/datasets/google/RSRCC.

08.
arXiv (CS.AI) 2026-06-12

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

arXiv:2606.12419v1 Announce Type: cross Abstract: Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction.

09.
arXiv (CS.CL) 2026-06-11

UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction

We propose UR-BERT, a Romanized transcription-based text-to-speech (TTS) encoder for massively multilingual TTS systems. Conventional grapheme-to-phoneme (G2P)-based approaches are limited to around 100 languages due to the availability of reliable G2P resources. In contrast, UR-BERT scales to 495 languages by unifying diverse writing systems into a shared Romanization representation. To further enhance phonetic fidelity and text-speech alignment, we introduce a speech token prediction objective during training, which encourages the encoder to learn speech-aware phonetic representations in a data-efficient manner. Experiments show that TTS systems built on UR-BERT consistently outperform recent text encoder baselines across a wide range of languages and resource conditions, and demonstrate strong generalization to unseen languages.

10.
arXiv (CS.CL) 2026-06-11

Models That Know How Evaluations Are Designed Score Safer

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

11.
arXiv (CS.AI) 2026-06-16

SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity

arXiv:2606.16003v1 Announce Type: new Abstract: This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding, multi-equation dependency, and humanaligned evaluation. To this end, we construct a dataset of AI research papers, pairing contextual passages with ground-truth equations and variable descriptions. We develop an explainable equation generation workflow and evaluate it across diverse open- and closed-source LLM backbones. We introduce an evaluation protocol combining automatic metrics, LLM-based rubrics, and human judgments to assess accuracy, explainability, and human-LLM alignment. Results indicate that LLMs perform moderately on lexical- and syntactic-based similarity, while struggling with semantic accuracy. Comparisons between LLM-based evaluations and human judgments reveal limited alignment, highlighting challenges in using LLMs to assess equation quality. These findings offer insights for improving equation generation models and developing more reliable evaluation methods for scientific text. We provide code and data for reproducibility.

12.
arXiv (CS.CV) 2026-06-15

Encoder Winners Do Not Reliably Transfer Across VLA Backbone Scale: A Frozen-Backbone Grafting Diagnostic

Vision-language-action (VLA) policies typically inherit their vision encoder from upstream VLM releases, but it is unclear whether an encoder choice validated on a small VLA transfers to a larger backbone. We introduce a frozen-backbone grafting diagnostic: the vision tower of a released VLA is replaced by a candidate encoder under a fixed protocol (adaptive average pooling, LayerNorm, and a single trainable linear projector), with the language model and action expert frozen. Across four encoders, two LIBERO suites, two backbones (SmolVLA-450M and $\pi_{0.5}$-3.3B), and two-to-three seeds per cell (40 main grafting runs plus native, LoRA, pooling, and zero-/shuffled-image controls, all scored by offline action MSE), the small-backbone winner does not reliably select the large-backbone top tier: SigLIP is best on SmolVLA across both suites, while on $\pi_{0.5}$ DINOv2-small leads the spatial suite and the object suite is a seed-sensitive near-tie band; three of the four backbone-suite comparisons (and 11 of 12 seed-level cells) support backbone-dependent rankings. The grafting wrapper is itself non-neutral with opposite sign across backbones (+45-56% MSE on the SmolVLA native tower, -50-52% on $\pi_{0.5}$), so all conclusions are conditional on the fixed grafting protocol. We position frozen grafting as a cheap target-backbone diagnostic to run before committing to an encoder at scale, not as a closed-loop deployment claim.

13.
arXiv (CS.CV) 2026-06-16

A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

In the context of novel view synthesis, 3D Gaussian Splatting (3DGS) has recently emerged as an efficient and competitive counterpart to Neural Radiance Field (NeRF), enabling high-fidelity photorealistic rendering in real time. Beyond novel view synthesis, the explicit and compact nature of 3DGS enables a wide range of downstream applications that require geometric and semantic understanding. This survey provides a comprehensive overview of recent progress in 3DGS applications. It first reviews the reconstruction preliminaries of 3DGS, followed by the problem formulation, 2D foundation models, and related NeRF-based research areas that inform downstream 3DGS applications. We then categorize 3DGS applications into three foundational tasks: segmentation, editing, and generation, alongside additional functional applications built upon or tightly coupled with these foundational capabilities. For each, we summarize representative methods, supervision strategies, and learning paradigms, highlighting shared design principles and emerging trends. Commonly used datasets and evaluation protocols are also summarized, along with comparative analyses of recent methods across public benchmarks. To support ongoing research and development, a continually updated repository of papers, code, and resources is maintained at https://github.com/heshuting555/Awesome-3DGS-Applications.

14.
arXiv (quant-ph) 2026-06-16

Quantum vortex in a fluid flow: negative effective mass and a novel mechanism for turbulence formation

arXiv:2606.15803v1 Announce Type: cross Abstract: We explore the movement of a thin, circular quantum vortex filament within an infinite cylindrical pipe. The fluid surrounding the vortex ring moves through the pipe at a non-zero velocity denoted by $v$. Our study examines the energy spectrum $E = E(p)$, where $p$ represents the total momentum of a vortex ring. We have demonstrated that the function $E(p)$ significantly depends on the velocity $v$. The discovered spectrum $E(p)$ reveals the existence of states with both negative and extremely large effective masses. We also explored the hypothesis regarding the existence of coupled vortex pairs possessing finite summary effective masses. Every pair consists of vortices that possess both positive and negative masses, with the magnitude of these masses being unrestricted. In our model, the criterion for the appearance of these states is based on comparing two numbers. The first is seen as a quantum counterpart to the Reynolds number, while the second represents its critical value for a flow with a single vortex. We also explore how this studied effect might contribute to the emergence of quantum turbulence. This study discusses a method for determining the critical Reynolds number in quantum turbulence, using the proposed model as a framework. Here, we use a new quantization technique for classical closed vortex filaments developed by the author earlier.

15.
arXiv (CS.AI) 2026-06-12

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

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\%.

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

CREST: Deployment-Realistic Hardware-in-the-Loop NAS for Embedded Sensing Systems

arXiv:2606.15004v1 Announce Type: cross Abstract: Deploying neural networks on low-power microcontrollers (MCUs) requires selecting model architectures under tight memory, latency, and energy constraints. Existing workflows often simplify this process along one or more axes: static proxy costs such as FLOPs or parameters, treating one MCU as representative, and continuous-inference tests instead of deployed sensing schedules. These assumptions can mis-rank Pareto-front candidates, miss infeasible deployments, and obscure schedule-dependent energy. We present CREST (Cross-platform Runtime Evaluation and Search Tool), a deployment-realistic hardware-in-the-loop (HIL) neural architecture search (NAS) framework for MCU sensing systems. CREST keeps the optimizer, HIL measurement boundary, logging, and replay workflow fixed while exposing workload, model family, target backend, schedule, quantization, and scoring policy as configurable axes. This makes deployment effects experimentally separable within one reusable workflow. We evaluate CREST on inertial odometry and audio classification across three Arm Cortex-M targets. For inertial odometry, measured-energy HIL search reduces median per-inference energy by 41.7% versus FLOPs-based selection and 40.8% versus memory-traffic-based selection at similar error. FLOPs-based selection also chooses infeasible deployments on memory-constrained targets. On the STM32 N657 target, continuous-inference and duty-cycled searches produce different Pareto frontiers. For audio classification, the same application-level policy selects different DS-CNN architectures on different boards, and cross-board replay changes deployment cost substantially. Overall, CREST shows that deployment-realistic MCU NAS must jointly optimize model architecture, target platform, runtime schedule, and deployment policy rather than relying only on static proxy costs or continuous-inference measurements.

17.
medRxiv (Medicine) 2026-06-11

Plasma protein prioritisation in rheumatoid arthritis reveals druggable targets and shared biology with cardiovascular diseases

Abstract Background Rheumatoid arthritis (RA) is an autoimmune inflammatory disease with complex and incompletely understood molecular mechanisms. Understanding circulating proteins associated with RA may improve understanding of disease biology and clarify its pathological links with cardiometabolic comorbidities. Methods A proteome-wide two-sample Mendelian randomisation (MR) drug target analysis was conducted using plasma proteins measured in 54,219 participants from the UK Biobank Pharma Proteomics Project as exposures and RA and cardiometabolic diseases as the outcomes. Summary statistics for RA included 53,663 cases and 1,070,200 controls. Colocalisation analysis was performed to confirm shared single causal variants and prioritise RA proteins supported by both MR and colocalisation. The prioritised proteins were then evaluated in the Accelerating Medicines Partnership RA Phase II synovial single-cell dataset for cell-type expression patterns. Druggability was then assessed followed by analysis of genetic overlap between RA-associated proteins and cardiometabolic diseases. Results 37 plasma proteins had a causal effect on RA risk, supported by combined evidence from MR and conditional colocalisation. In synovial tissue, TPPP3, RARRES2, AKAP12, and GGT5 were predominantly expressed in stromal and endothelial cell clusters. Druggability assessment identified IFNGR2, IL6R, CD40, and FCGR2B as Tier 1 targets. However, several biologically relevant proteins, including RARRES2, AKAP12, TPPP3, and SNX2, had limited available druggability data. Genetic overlap analysis demonstrated shared protein signals between RA and cardiovascular diseases, including overlap of RARRES2 and TPPP3 with coronary artery disease (CAD) and FCGR2B with atrial fibrillation (AF). To approximate the therapeutic effect of target inhibition, the direction of effect estimates for proteins showing overlap between RA-CAD and RA-AF was reversed. Conclusion This study identified circulating proteins involved in RA pathogenesis and reveals shared mechanisms between RA and cardiovascular diseases. While some proteins showed clear translational potential targets, several prioritised proteins had limited available druggability information and could not be confidently classified. Addressing these gaps may help identify new targets relevant to RA management. Future work should also use phenome-wide MR studies to evaluate potential on-target adverse effects of protein inhibition across RA-CAD and RA-AF.

18.
arXiv (CS.CL) 2026-06-12

Agent-based models for the evolution of morphological alternation patterns

Why is the past of English "go" the apparently unrelated "went"? Such alternations are frequent in languages. They neither aid communication nor learnability, yet they can be persistent, surviving over centuries or millennia. We present a multi-agent simulation of the emergence of morphological stem and inflection alternations. Alternate forms arise by phonological changes or, as with "go/went", from lexical alternatives associated with a subset of the population. When an agent 'hears' another agent use a novel form for a slot in the paradigm of a word (say, the past tense of go), they will with some probability adopt that form, possibly spreading its use to other slots in the paradigm that shared the same original form. Thus alternative forms can spread through the population and become entrenched as stem or inflectional marker alternants. Unlike many previous computational studies, our system allows for naturalistic lexical forms, realistic phonological rules, lexicons with hundreds or thousands of entries, and agent populations in the tens or hundreds. It supports several network topologies, diffusion patterns and agent adoption policies. One issue with such simulations is evaluation: how realistic is the resulting morphology compared to those of real languages? We introduce the AI Historical Linguist, a novel Large Language Model-driven system that models a debate between two historical linguists. We use this to compare a set of real language morphologies, disguised morphologies, and experimentally evolved morphologies. The results suggest that among the factors that favor more plausible morphologies are scale-free social networks and random Bernoulli adoption of forms. We also present three case studies modeling attested historical changes, allowing us to test what might have happened if history had been different. All code and data are released.

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

See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL

Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference. The prevailing training paradigm relies on large-scale caption-based pretraining for general alignment, followed by supervised fine-tuning and reinforcement learning to enable instruction following and complex reasoning. However, such pretraining provides only weak visual grounding: short, coarse captions bias models toward salient objects while neglecting fine-grained visual evidence. In this paper, we introduce Visual Evidence Pre-Alignment (VEPA), an intermediate stage between pretraining and post-training that explores a novel sufficiency-driven objective with Group Relative Policy Optimization (GRPO) to optimize question-conditioned visual evidence descriptions. Extensive experiments across diverse benchmarks show that our VEPA consistently enhances performance on visually demanding evaluations and complements standard supervised post-training. Further analyses show that the income stems from strengthened, transferable visual grounding, rather than from additional task-specific training.

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

SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG

Fixed-length chunking in Retrieval-Augmented Generation (RAG) often leads to boundary fragmentation, where critical evidence is split across segments, degrading retrieval recall. While static windowing and parent retrieval improve recall, they introduce significant token overhead. We propose SCAR (Semantic Continuity-Aware Retrieval), an adaptive retrieval policy that selectively expands neighboring chunks by weighing query-neighbor relevance against a structural continuity penalty. SCAR uses a relative expansion threshold tied to each retrieved chunk's own query-relevance, yielding an approximately scale-invariant decision rule that transfers across embedding models without recalibration. Across four diverse corpora (RFC, GDPR, a 10-K report, and a Merger agreement; N=320 queries; 160 boundary-fragmented), SCAR achieves 92.8% recall on boundary-fragmented queries with only 7.84 chunks, a 22.9% reduction compared to static windowing (10.16 chunks). Paired bootstrap tests (B=10,000) confirm the chunk reduction is highly significant (p

21.
arXiv (CS.CL) 2026-06-18

ForecastBench-Sim: A Simulated-World Forecasting Benchmark

Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the world is simulated, the same setup can generate continuous or binary forecasting questions at arbitrary time horizons, paired intervention worlds for conditional or causal questions, and resolved examples of rare or disruptive outcomes. We describe the benchmark pipeline, question families, scoring protocol, and release artifacts, and report validation slices from model evaluations and an anonymized human pilot. ForecastBench-Sim is intended to complement real-world forecasting benchmarks by providing controlled, immediately resolvable tasks for studying probabilistic reasoning under dynamic world states.

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

MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

arXiv:2603.01131v3 Announce Type: replace-cross Abstract: Clinical diagnosis is a gradual process of evidence integration, in which physicians move from symptoms and medical history to examinations, competing hypotheses, disease relations, and treatment decisions. Large language models have advanced medical text understanding and generation. Yet their clinical use remains limited by weak evidence grounding, opaque reasoning, and inconsistent links among differential diagnosis, final diagnosis, diagnostic basis, and treatment planning. We introduce MedCollab, a multi-agent framework for full-cycle clinical diagnosis and report generation. MedCollab coordinates specialist and examination agents according to patient records. It structures agent deliberation with an Issue-Based Information System (IBIS) protocol, so that each diagnostic position is supported by patient-specific evidence and medical knowledge. It also builds Hierarchical Disease Relation Chains (HDRC) to connect accepted hypotheses through progression, complication, and comorbidity relations. During multi-round deliberation, a verifier-guided consensus module evaluates evidence support, medical plausibility, and logical conflicts. It then adjusts agent contributions and filters unsupported reasoning. Experiments on ClinicalBench and MIMIC-IV show that MedCollab outperforms leading LLMs and medical multi-agent baselines in diagnostic accuracy, evidence consistency, and clinical reasoning quality. These results indicate that structured and auditable collaboration can produce more faithful and clinically coherent diagnostic reports.

23.
arXiv (CS.LG) 2026-06-19

The Correctness Illusion in LLM-Generated GPU Kernels

arXiv:2606.20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks. The number of inputs varies between benchmarks. The shape, dtype, and tolerance are fixed for each kernel. We test that oracle empirically. We construct a controlled corpus of 24 Triton and CPU stand-in kernels (15 correct controls and 9 LLM-style buggy variants seeded with documented transcription errors) and re-evaluate it under op-schema-aware seeded fuzzing with a high-precision (fp64) CPU reference and per-(op, dtype) absolute tolerances. The seeded oracle flags 9 of 9 buggy kernels and passes 15 of 15 correct controls, at zero precision cost on controls. We extend the corpus to 26 ops (adding a flash-attention pair) and re-run the same protocol on five GPU classes (RTX 3060, A10, L40S, A100 SXM4, H100 NVL). The verdicts are identical across all five GPUs: 10 of 10 illusions caught and 16 of 16 controls clean. The corpus result is about LLM-style transcription bugs that the allclose-on-one-shape oracle certifies as correct, not about the bug rate of any specific deployed LLM. Every flagged failure replays byte-for-byte from a stored seed.

24.
medRxiv (Medicine) 2026-06-15

Therapeutic efficacy study on shoulder impingement syndrome in swimmers: a network meta-analysis

Shoulder impingement syndrome (SIS), including subacromial impingement and rotator cuff tendinitis, is commonly caused by repetitive swimming movements and associated shoulder joint dysfunction. Despite numerous available treatment options, no consensus exists on the most effective treatment option. Therefore, this systematic review and network meta-analysis aimed to investigate treatment methods for SIS in swimmers. Using a frequentist framework and Cochrane PICOS principles, we compared SIS treatments, constructed network evidence diagrams, and assessed heterogeneity. A total of 45 studies were included in the qualitative synthesis, and 42 contributed to the network meta-analysis, comprising 1752 participants, 9 treatment categories, and outcome measures. For pain outcomes, some adjunctive interventions combined with exercise showed favorable ranking probabilities, although several estimates were accompanied by wide confidence intervals. For shoulder range-of-motion outcomes, taping, acupuncture, manual therapy, and sport-specific training showed favorable effects in selected comparisons, particularly for external and internal rotation. According to surface under the cumulative ranking curve (SUCRA) rankings, exercise combined with medium-frequency therapy ranked highly for pain reduction, whereas exercise combined with acupuncture or extracorporeal shock wave therapy ranked highly for shoulder flexion. Exercise combined with taping ranked highly for external rotation, and exercise combined with manual therapy ranked highly for internal rotation. However, the interpretation of ranking results should remain cautious because uncertainty and inconsistency were present in some comparisons. Exercise-based rehabilitation appears to remain central to the management of SIS in swimmers. Several adjunctive interventions showed favorable findings for selected outcomes, especially pain relief and shoulder rotational function. However, the available evidence was affected by heterogeneity, inconsistency, and imprecision across some treatment comparisons. More rigorously designed swimmer-specific randomized controlled trials are needed before firm treatment hierarchies can be established. Trial registration: The protocol for this systematic review is registered with PROSPERO (www.crd.york.ac.uk/PROSPERO; registration number: CRD42024498851). The first submission of PROSPERO was on January 15, 2024, and it was revised and updated on March 25, 2026.

25.
arXiv (CS.CL) 2026-06-19

Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation

Automated medical report generation (MRG) is increasingly used to reduce the burden of manual reporting and for decision support. Large vision-language models (LVLMs) hold great promise for automated MRG due to their fine-grained image-text alignment and advanced text-generation capabilities. Currently, state-of-the-art MRGs primarily focus on adapting pre-trained LVLMs with direct supervised fine-tuning (SFT), a fine-tuning strategy with medical image-report pairs. However, several factors limit the performance of these LVLMs. Firstly, direct SFT enables LVLMs to generate medical reports directly without an intermediate thinking process of pathological feature perception and diagnostic reasoning. This causes a potential failure to perceive pathological features and thus leads to misdiagnosis. Secondly, direct SFT lacks the incorporation of radiology-specific knowledge guidance, causing LVLMs to misinterpret perceived pathological features and make incorrect diagnoses. To address these gaps, we propose a novel fine-tuning strategy named Med-R2. We introduce a perception-driven long reasoning process that precedes report generation and incorporates radiology-specific knowledge as guidance. Additionally, to alleviate potential perceptual errors in complex reasoning, a reflection mechanism is introduced to refine the perception of pathological features and the generated report. Our experiments demonstrate that Med-R2 effectively enhances the capability of pathological features perception and diagnosis accuracy for MRG via fine-tuned LVLMs.