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 (quant-ph) 2026-06-12

Matrix phase-space representations for gaussian boson sampling

arXiv:2503.12749v2 Announce Type: replace Abstract: We introduce coherent matrix phase-space distributions. These use conservation laws and symmetries to improve the accuracy and speed of quantum phase-space representations. As an example, this is applied to validation of low-loss Gaussian boson sampling (GBS) quantum computational advantage experiments, where classical generation of the random photon-number counts is exponentially hard. Large improvements in sampling errors are demonstrated compared to previous methods. Matrix phase-space representations also provide a large numerical speed-up, due to their (at worst) quadratic scaling, compared to other methods for validating total count probabilities of large-scale, low-loss GBS networks.

02.
arXiv (CS.AI) 2026-06-17

Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics

arXiv:2606.17581v1 Announce Type: cross Abstract: We present a dependent-type-based prover designed around the way LLMs (and humans) tend to write mathematics, complementing existing systems such as Lean and Rocq. Its core design choices are a surface that imitates mathematical natural language and a rule-driven automation layer that closes the routine steps a textbook would omit, so that an accepted proof can be re-emitted as a checked Lean file. Early experiments suggest that, even without any prover-specific training data, LLMs can learn to use it effectively on the miniF2F benchmark. Lean output excerpts: https://github.com/xiyuzhai-husky-lang/visored/

03.
arXiv (math.PR) 2026-06-11

Stochastic epidemic model with varying infectivity and waning immunity: the law of large numbers with unbounded infectivity

arXiv:2606.11845v1 Announce Type: new Abstract: We revisit the large population limit of our epidemic model with infection age dependent infectivity and progressive immunity waning, under the assumption that the supremum in $t$ of the random infectivity function has a finite expectation, while the previous proofs assumed that this supremum admits a deterministic upper bound.

04.
arXiv (quant-ph) 2026-06-12

Approximability limits for bounded-degree max-LINSAT and implications for decoded quantum interferometry

arXiv:2606.13570v1 Announce Type: new Abstract: For general max-k-XORSAT with $k \geq 3$, no polynomial-time algorithm can do substantially better than random guessing on worst-case instances unless $\mathsf{P} = \mathsf{NP}$: approximating beyond the random-assignment value of $1/2$ is $\mathsf{NP}$-hard. The picture changes when each variable appears in at most $D$ constraints. In that bounded-degree setting, polynomial-time algorithms can provably beat the random baseline by an additive amount of order $1/\sqrt{D}$. For Boolean instances, this scaling is known to be optimal: the matching hardness result is due to Trevisan, while the corresponding algorithmic guarantee was established by Barak et al. Whether the same holds over general finite fields, and what it implies for quantum algorithms, has not been established. We make this connection explicit and extend the hardness to max-E$k$-LINSAT$(q,r)$ with bounded degree $D$ and over arbitrary finite fields $\mathbb{F}_q$, proving that it is $\mathsf{NP}$-hard to exceed $r/q + \mathcal{O}_{q,r}(1/\sqrt{D})$. These results provide the complexity-theoretic benchmark for the bounded-degree instances targeted by decoded quantum interferometry (DQI), QAOA, and classical heuristics. Any quantum advantage on bounded-degree instances is therefore confined to the constant prefactor. We further show that in the context of DQI and on $(k,D)$-regular instances, this prefactor is sensitive to the nature of the decoder: DQI with classical decoders faces an information-theoretic $1/\sqrt{D \log D}$ barrier that prevents it from matching the hardness scaling, while DQI with quantum decoders is compatible with the $1/\sqrt{D}$ scaling – identifying quantum decoding as the key ingredient for matching the complexity-theoretic scaling with DQI.

05.
bioRxiv (Bioinfo) 2026-06-17

DesignMaster: A Multi-Conditional Diffusion Framework for Rational PROTAC Design

Motivation: Proteolysis-targeting chimeras (PROTACs) enable targeted protein degradation through ternary complex formation with E3 ubiquitin ligase. However, the rational design of PROTACs remains highly challenging due to limited structure-activity relationship data and the vast conformational diversity of linkers. Existing computational approaches can be broadly divided into structure-based ternary modelling methods and fragment-based linker generation models. Although these approaches have advanced PROTAC design, they typically neglect key physicochemical constraints and linker-length control during the generation process, causing the generated PROTACs to lack balanced structural properties required for effective ternary complex formation with drug-like characteristics. Results: To address these limitations, we propose DesignMaster, a diffusion-based generative framework that explicitly incorporates linker length and physicochemical properties as controllable conditioning signals. DesignMaster employs an E(3)-equivariant graph Transformer with a gated multi-condition fusion module to inject linker length and physicochemical constraints throughout the diffusion process, enabling fine-grained and constraint-aware molecular generation. Experiments on PROTAC-DB 2.0 and 3.0 demonstrate that DesignMaster outperforms state-of-the-art baselines, with a 3.2% improvement in validity and a 34.4% improvement in recovery. The Case study shows DesignMaster achieves a 51.78% reduction in RMSD when predicting the linker of PROTAC BCPyr targeting 6W7O, highlighting its potential for practical structure-guided PROTAC design. Availability: The source code and datasets are available at https://github.com/ABILiLab/DesignMaster.

06.
medRxiv (Medicine) 2026-06-11

Vascular Phenotyping in Parkinson's Disease: Diabetes Mellitus Operationalizes a Microvascular Metabolic Syndrome Cluster Across PPMI Diagnostic Cohorts

Background: Diabetes mellitus elevates Parkinson's disease (PD) risk, via hypothesized cerebrovascular mediation. Whether the diabetes/prediabetes vascular-risk phenotype concentrates in cardiometabolic risk or macrovascular events across prodromal and clinically diagnosed PD remains unresolved. Objectives: To quantify the vascular-risk burden associated with diabetes/prediabetes across the PPMI diagnostic cohorts to test whether this association differs by cohort. Methods: Cross-sectional analysis of 413 PPMI participants (76 healthy controls, 145 prodromal PD, 192 clinically diagnosed PD) examined diabetes/prediabetes (n = 73) and seven vascular risk factors. The Vascular Burden Score (0 to 7) was a priori partitioned into microvascular and macrovascular sub-scores. Modified Poisson regression estimated adjusted prevalence ratios (aPR), adjusted for age, sex, and body mass index. A cohort-by-diabetes interaction tested cross-cohort consistency. Sensitivity analyses incorporated nigral diffusion tensor imaging (PD-risk biomarker) and FreeSurfer white matter hypointensity volume (cerebrovascular marker). Results: Diabetes/prediabetes elevated Vascular Burden Score ({beta} = 0.53, 95% CI 0.29 to 0.77, p < 0.001) versus non-diabetic participants, with a non-significant cohort-by-diabetes interaction (F = 0.29, p = 0.747). Three microvascular factors survived false discovery rate correction: obesity (aPR 2.28), hypertension (aPR 1.60), and hyperlipidemia (aPR 1.45). Macrovascular events showed no diabetic amplification ({beta} = -0.06, p = 0.25). In the imaging-phenotyped subset, Vascular Burden Score components contributed classifier variance distinct from nigral microstructure. Conclusions: Diabetes/prediabetes operationalize a microvascular cluster stable across prodromal and idiopathic PD. Cardiometabolic phenotyping may complement established PD-risk biomarkers (dopamine transporter SPECT, nigral diffusion), pending longitudinal validation linking vascular phenotype to dopaminergic markers.

07.
arXiv (quant-ph) 2026-06-12

Quantum metrology via partial quantum error correction

arXiv:2605.08341v2 Announce Type: replace Abstract: We introduce a method for error-corrected quantum metrology where only partial quantum error correction (QEC) is needed to suppress local noise and maintain the probe states' super-standard-quantum-limit (super-SQL) sensing performance. This stands in contrast to the existing QEC-assisted sensing schemes in Phys. Rev. Lett. 112, 080801 (2014) and Phys. Rev. Lett. 112, 150802 (2014), where a probe state is encoded into the logical subspace of a quantum code and error correction involves measurements on all checks of the code. Here, we encode the probe states into superpositions of energetically different states of the underlying quantum code. For our probe states, error correction using a subset of checks is enough to suppress noise both before and after phase imprinting. We analyze the tradeoff in noise suppression. For noise parallel to our phase imprinter of weight $l$, we achieve a suppression of $p^\delta$ where $p$ is the noise strength and $\delta = \lfloor (l+1)/2 \rfloor$. We propose an adaptive imprinter weight increasing strategy to maintain super-SQL performance as we scale up the system. In all our examples, checks and phase imprinters are chosen to be local operators avoiding non-local connectivity.

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

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment

arXiv:2606.13176v1 Announce Type: new Abstract: Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical for effective intervention. Recently, large language models have been explored for mental health assessment. However, existing general-purpose post-training methods do not align with the cognitive processes of human assessment, which may lead to unreliable reasoning outcomes. To bridge this gap, we propose Cognitive Relative Policy Optimization (CRPO), a reinforcement learning framework tailored for the mental health domain. CRPO extends group relative policy optimization by integrating stage-dependent uncertainty modeling into the policy optimization process. Specifically, we introduce a stage-wise entropy regularization mechanism that encourages broad exploration in early reasoning phases and progressively enforces confident decision-making in later stages, mimicking the human cognitive shift from uncertainty to certainty. In addition, inspired by cognitive appraisal theory, we formalize cognitive reasoning stages, thereby guiding theory-grounded interpretable inference. Experiments on 8 mental health datasets show that CRPO achieves an average improvement of 10.4 percentage points in weighted F1-score over the best reinforcement learning baseline. Furthermore, the CRPO-trained model Mental-R1 demonstrates clear advantages compared with existing large language models on reasoning-intensive cases, suggesting that CRPO enhances reasoning capabilities for mental health assessment.

09.
arXiv (CS.LG) 2026-06-12

Uncertainty Estimation for Molecular Diffusion Models

arXiv:2606.13451v1 Announce Type: new Abstract: Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.

10.
Nature Medicine 2026-06-17

Why large-scale randomized trials of live-attenuated shingles vaccination for dementia prevention are urgently needed

In my view, we have never had as robust a body of evidence from observational data on an intervention for dementia as we do for live-attenuated shingles vaccination. Both a recent US National Institutes of Health expert workshop and an international expert consensus on Alzheimer’s disease drug repurposing identified large-scale randomized trials of shingles vaccination for dementia prevention as the crucial next step for the field.

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

DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning

Reasoning capabilities of multimodal large language models (MLLMs) have improved considerably in recent years. Existing approaches typically rely on explicit chain-of-thought or continuous latent-space trajectories to enhance multi-step reasoning. However, these methods generally assume that an input admits a single latent interpretation and unfold reasoning along a fixed path or under a uniform computation budget. In real-world multimodal settings, visual observations are often subject to occlusion, blur, viewpoint variation, or semantic ambiguity, giving rise to multiple plausible interpretations. A uniform reasoning strategy not only limits the model's ability to explore multiple hypotheses but also incurs high memory usage and rollout cost. We present DLWM (Diverse Latent World Models), a multimodal reasoning framework that combines latent-space reasoning with reinforcement learning. First, we construct a set of diverse latent world hypotheses in continuous latent space, each capturing a different plausible interpretation of the visual input, and unfold latent reasoning independently on each hypothesis. An orthogonality-based diversity regularizer explicitly prevents hypothesis collapse. Second, we formulate the latent reasoning process as a resource-constrained sequential decision problem and introduce a resource-aware reinforcement learning policy that adaptively allocates computation across hypotheses, dynamically deciding whether to expand, terminate, or merge reasoning paths, thereby substantially reducing memory footprint and improving rollout efficiency. Experiments on multiple multimodal reasoning benchmarks demonstrate that DLWM outperforms existing methods by 2-5 points in accuracy while reducing memory usage by 24%.

12.
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.

13.
arXiv (CS.CL) 2026-06-15

FineDialFact: A benchmark for Fine-grained Dialogue Fact Verification

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.

14.
medRxiv (Medicine) 2026-06-17

Trends in Suicide Mortality by Method among US Individuals aged 10-24 Years from 1999 to 2024

Background: Suicide is the second leading cause of death in US adolescents aged 10-24. Method use strongly influences lethality and design of prevention strategies, but recent trends remain unclear. We therefore aimed to investigate trends in suicide mortality rates by method, age group, and sex. Methods: This cross-sectional study used suicide mortality data from the National Center for Health Statistics for a quarter-century period, between 1999 and 2024. All individuals aged 10-24 years at the time of death, with suicide as the underlying cause, were included. We estimated suicide mortality rates (i.e., the number of suicide deaths per 100,000 people) and annual percent change by method (firearm, asphyxiation, poisoning, other), age group (10-14, 15-19, 20-24), and sex. Changing trend time points were determined using Joinpoint regression models Results: From 1999 to 2024, 159,241 suicide deaths occurred among individuals aged 10-24. While suicide rates declined across all age groups between 2017 and 2024, the male-to-female gap narrowed by 18.9%. Among 10-14-year-olds, declining rates among males masked a consistent increase in female suicide rates since 2011. Although asphyxiation-related suicides decreased across all groups since 2018, firearm suicide rates increased for females in the 10-14 and 20-24 age groups. Albeit not as common as firearms or asphyxiation, poisoning suicide rates increased in the 15-19 and 20-24 age groups. Since 1999, suicide rates by other less common methods (e.g., jumping) showed significant increases, for both sexes, especially among individuals aged 20-24. Suicide rates were consistently highest in the 20-24 age group across all study years. Conclusion: The decrease in suicide mortality rates among individuals aged 10-24 was largely driven by declines in males and reductions in asphyxiation-related suicides. However, increasing female suicide rates in the 10-14 age group, as well as increasing rates of death by less common means, warrant close attention. While suicide prevention efforts like structural interventions and means restriction have shown effectiveness among male adolescents, priority should now be given to adapting these approaches for female adolescents, particularly those aged 10-14.

15.
arXiv (CS.LG) 2026-06-17

Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery

arXiv:2606.17782v1 Announce Type: new Abstract: Primary motivation in blind inverse problems is to recover signals of interest from corrupted observations without knowing the obfuscating mechanism. Blind deconvolution is a prominent approach when the corruption is convolutional, but it is not applicable when general linear transformations obfuscate the domain structure. In this work, we propose an unsupervised framework for recovering latent domains and signals by discovering symmetries of the data distribution. Our framework models observations as linear measurements of signals sampled from a latent random field, and optimizes a shallow group-convolutional network by imposing stationarity and locality regularization at the model output. The model learns a latent symmetry action and an appropriate filter, thereby mapping unstructured observations to a symmetry-based representation that reveals latent signals. Experiments on stochastic processes, Ising models, shuffled and bit-scrambled images, and neural recordings show that the method recovers latent domains and signals from unstructured observations, suggesting symmetry discovery as a new direction for unsupervised structure learning and blind inverse problems.

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

Counterexample Guided Learning in the Large using Reasoning Agents

arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

17.
arXiv (CS.CL) 2026-06-11

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks. However, most existing creativity metrics are tightly coupled to specific tasks, embedding domain assumptions into the evaluation process, and limiting scalability and generality. To address this gap, we introduce an automated, domain-agnostic framework for quantifying LLM creativity across open-ended tasks. Our approach separates the measurement apparatus from the creative task itself, enabling scalable, task-agnostic assessment. Divergent creativity is measured using semantic entropy, a reference-free and robust metric for novelty and diversity, validated against human annotations, LLM-based novelty judgments and baseline diversity measures. Convergent creativity is assessed via a novel retrieval-based multi-agent judge framework that delivers context-sensitive evaluation of task fulfilment with over 60% improved efficiency. We validate our framework in three qualitatively distinct domains: problem-solving (MacGyver), research ideation (HypoGen), and creative writing (BookMIA), using a broad suite of LLMs. Empirical results show that our framework reliably captures key facets of creativity, including novelty, diversity, and task fulfilment, and reveal how model properties, such as size, temperature, recency, and reasoning, impact creative performance. Our work establishes a reproducible and generalizable standard for automated LLM creativity evaluation, paving the way for scalable benchmarking and accelerating progress in creative AI.

18.
arXiv (CS.AI) 2026-06-15

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties

arXiv:2606.14240v1 Announce Type: new Abstract: Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and increasingly critical for Large Language Models (LLMs). However, existing affordance benchmarks largely expose explicit object identities in the evaluation setup, allowing models to rely on memorized object-affordance mappings rather than reasoning over physical properties. To address this gap, we introduce Affordance20Q, a novel affordance reasoning benchmark formulated as a 20-Questions game without exposing the object's identity. In each game, the model identifies a hidden object's affordance from a candidate set by asking yes/no questions about its physical properties. Affordance20Q comprises 1,009 games over 454 objects and 59 affordances, all manually filtered, refined, and annotated. We conduct comprehensive experiments with 15 state-of-the-art LLMs and find a substantial gap (~20 points) compared to human performance. A KL-based information-gain (IG) analysis further shows that models fail to ask discriminating questions as the game progresses. To close the gap, we develop KB-Anchored Rule Induction (KARI), a pipeline based on LLMs that generates affordance rules grounded in evidence from knowledge bases (KBs). KARI improves open-source LLMs by up to 15.2 points, while the limited coverage of KBs hinders further gains. We release all our code and data at https://github.com/1171-jpg/Affordance20Q.git

19.
arXiv (CS.CL) 2026-06-16

Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Sequential fine-tuning of Large Language Models (LLMs) adaptation to target tasks often triggers catastrophic forgetting, where the acquisition of novel target skills degrades ancestral capabilities. This paper presents a systematic comparative study of catastrophic forgetting across twenty premier models representing the state-of-the-art in mid-2026. We categorize our investigation into two primary research lines: (i) a behavioral and semantic output drift analysis of ten leading closed-source models (including Claude Fable 5, GPT-5.5 High, and Gemini 3.5 Flash), and (ii) a deep mechanistic interpretation of ten prominent open-weight architectures (such as DeepSeek-V4-Pro, Llama 4 Maverick, and Qwen 3.6-27B). Through weight-space trajectory tracking, Centered Kernel Alignment (CKA), and routing gate drift calculations in Mixture-of-Experts (MoE) layers, we localize the neural circuits highly susceptible to parameter overwriting. Our findings indicate that early-layer attention heads exhibit systemic entropic dispersion, while mid-to-deep feed-forward networks (or sparse expert blocks) suffer localized representation collapse. Informed by these insights, we introduce Low-Rank Circuit Projection (LRCP), a subspace-regularized training intervention. Empirical evaluations show that LRCP successfully mitigates up to 94.2% of ancestral capabilities in open-weight configurations and matches the adaptation velocity of standard PEFT baselines.

20.
arXiv (CS.CL) 2026-06-12

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ ArogyaSutra/

21.
arXiv (CS.CL) 2026-06-16

Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering

Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with five state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, GPT-oss-20B) on three benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model chain-of-thought reasoning and chain-of-thought-based majority voting. Results: Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains. Conclusion: The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.

22.
arXiv (CS.CL) 2026-06-11

Language Shapes Mental Health Evaluations in Large Language Models

Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening, and content moderation. This raises a reliability question: do semantically equivalent mental health inputs elicit comparable evaluations across languages, or systematic shifts consistent with language-associated social and cultural contexts? We examine this question in an English-Chinese setting with GPT-4o and Qwen3-32B using a two-level framework: construct-level evaluative orientation, measured by psychometric stigma instruments, and decision-level behavior, measured by binary stigma detection and four-class depression severity classification. Across instruments and models, Chinese prompts elicit higher stigma-related scores than English prompts. At the decision level, Chinese prompts reduce sensitivity to stigmatizing content and produce more conservative depression severity judgments, leading to more under-estimation errors. These findings show that prompt language can shift both evaluative orientation and downstream behavior in LLM-based mental health evaluation. They highlight the need to evaluate multilingual LLMs not only for aggregate performance, but also for whether they apply comparable evaluative standards across languages in socially sensitive domains.

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

DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents

arXiv:2511.20709v2 Announce Type: replace-cross Abstract: Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge. We present DualGauge, the first fully automated framework for jointly evaluating correctness and security of specification-only code generation, supported by DualGauge-Bench, a language-agnostic benchmark of 307 coding tasks each paired with functional and security tests derived from the same specification. Evaluating 10 representative LLMs across Python, C++, and JavaScript, we find that functional correctness substantially overestimates reliable code generation: even the strongest model remains below 15% joint security-functionality success in every language. Common model-side factors–scale, extended thinking, quantization, instruction tuning, and code specialization–do not reliably improve joint performance, suggesting secure-and-correct code generation does not simply emerge from stronger coding capability. Evaluation of 3 leading agentic coding systems (Codex, OpenHands, and Claude Code) shows that iterative scaffolding provides no advantage over direct (LLM-based) generation on specification-only tasks. A qualitative audit reveals failures concentrate at the output contract boundary and in guards that exist but are insufficient–patterns that only joint benchmarking reliably exposes.

24.
arXiv (CS.AI) 2026-06-15

CARE: Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation

arXiv:2606.14581v1 Announce Type: cross Abstract: Granting LLMs direct control over costly, irreversible scientific experiments leads to unsafe exploration and unstable performance, but discarding LLM creativity entirely sacrifices significant optimization potential. We introduce CARE (Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation), an auditable controller for high-throughput experimentation (HTE) optimization that keeps a non-LLM incumbent optimizer as the default action path while using LLMs to revise challenger ranking policies. Before each outcome is revealed, a public-evidence intervention gate compares the challenger with the incumbent. It authorizes the challenger's selection only when the evidence available before selection supports the change, with the decision recorded in the audit log. CARE outperforms all other evaluated methods on Minerva/Olympus and ChemLex benchmarks, with final-best improving from 80.0 to 88.5 on Minerva/Olympus and from 83.9 to 92.1 on ChemLex, relative to the public incumbent. Our experiments indicate that LLM self-evolution is more reliable when it expands the proposal space under an auditable controller, rather than directly choosing experiments.

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

Text region detection in historical astronomical diagrams

Text detection is a crucial task in the analysis of historical documents. While datasets and benchmarks exist for text detection in manuscripts and maps, the study of text in mathematical diagrams has received little attention. To address this, we introduce a large-scale, diverse, open-access dataset of 948 historical astronomical diagrams containing 10,940 oriented polygonal text regions. Our dataset spans ten centuries (8th to 18th) and seven main linguistic traditions: Arabic and Persian (115), Chinese (332), Byzantine (233), Latin (185), Hebrew (48), and Sanskrit (35). It captures a wide range of diagram styles and textual content, from symbols to multi-line paragraphs. Each text instance is annotated with ordered polygons that precisely delineate text regions and encode the reading direction. In addition, we annotated the 2,293 regions in Latin diagrams with 20 class labels. We evaluated several strong baselines on our dataset, including TESTR, DeepSolo++, and Poly-DETR, a simple extension of DINO-DETR that we design to predict ordered polygon vertices. Poly-DETR achieves state-of-the-art performance on the MTHv2 and cBAD2019 benchmarks and provides a solid, simple baseline on our dataset. Code and dataset available online.