中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.AI) 2026-06-19

CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions

Authors:
Akshat Dasula↗Prasanna Desikan↗Jaideep Srivastava↗Shivali Dalmia↗Abhishek Mukherji↗

arXiv:2604.05435v2 Announce Type: replace Abstract: Incomplete or inconsistent discharge documentation drives care fragmentation and avoidable readmissions. Despite its critical role in patient safety, auditing discharge summaries relies on manual review and does not scale. We propose an automated framework for auditing discharge summaries using large language models (LLMs). Our approach operationalizes the DISCHARGED framework into a checklist of 46 questions. Using 50 summaries from the MIMIC-IV database, with clinician ground-truth labels, we benchmark 11 LLMs. Model-assessed mean documentation completeness ranges from 54.9% to 74.2%, and the best-performing models achieve a Cohen's kappa values around 0.5 against clinician labels, indicating moderate agreement. All models struggle to identify ambiguous documentation (Unclear), highlighting a key gap in current automated auditing. This work provides a clinician-validated benchmark and zero-shot baselines for systematic quality improvement in clinical documentation.

Read & Discuss → View Source →
02.
arXiv (CS.CL) 2026-06-12

A Unifying Lens on Reward Uncertainty in RLHF

Authors:
Ely Hahami↗Yoel Zimmermann↗Ray Zhou↗Jack Benarroch Jedlicki↗

Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is pessimism: lowering rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a distributional reward model $p(r\mid x,y)$. Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward $\tilde r(x,y) = \pm\beta\log\mathbb{E}_p[e^{\pm r/\beta}]$. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-25

LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges

Authors:
Thi Huyen Nguyen↗Zahra Ahmadi↗

The rapid growth of scientific submissions has pushed traditional peer review toward its scalability limits, motivating the exploration of large language models (LLMs) as intelligent automated evaluation assistants. Although recent studies show that LLMs can generate fluent critiques and approximate reviewer scores, their reliability, robustness, and security as decision-support systems remain insufficiently understood. This survey offers a systems-level analysis of LLM-based scientific peer review, focusing on two core evaluative functions: critique generation and score prediction. We present a structured taxonomy of modeling approaches (including prompt-based, supervised, retrieval-augmented, and alignment-optimized approaches), and synthesize empirical findings across existing benchmarks. We analyze dataset constraints, evaluation shortcomings, and domain concentration biases that limit current assessment practices. Beyond performance metrics, we identify emerging robustness risks, including prompt injection, data poisoning, retrieval vulnerabilities, and reward hacking, which expose automated review pipelines to strategic manipulation. From a data mining perspective, we outline key open challenges in modeling subjective disagreement and cross-domain generalization. By reframing automated peer review as a high-stakes, multi-objective decision problem, this survey provides a roadmap for developing robust, transparent, and trustworthy AI-assisted scientific evaluation systems.

Read & Discuss → View Source →
04.
arXiv (math.PR) 2026-06-18

Functional central limit theorems for non-local branching Markov processes

Authors:
Christopher B. C. Dean↗Emma Horton↗

arXiv:2502.19382v2 Announce Type: replace Abstract: The aim of this paper is to study the fluctuations of a general class of supercritical branching Markov processes with non-local branching mechanisms. We establish functional central limit theorems and show that the limiting behaviour falls into three regimes, determined by the size of the spectral gap associated with the first-moment semigroup of the branching process. The main novelty is to develop a unified functional fluctuation theory for spatial branching Markov processes with non-local reproduction, allowing a general finite-dimensional spectral structure for the first-moment semigroup, including non-simple leading eigenvalues and nilpotent Jordan-type components. In doing so, we extend the classical small, critical and large fluctuation trichotomy beyond the finite-type and local spatial settings, and obtain limiting processes that capture the covariance structure induced by non-local offspring displacement.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-16

Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers

Authors:
Roko Peran↗Luka Hobor↗Mihael Kovac↗Mario Brcic↗

arXiv:2606.15577v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly involved in complex mathematical optimization, even if the pragmatic user who triggers them is unaware of it. After all, many real-world problems reduce to the search for better or the best solutions. The field of LLM-as-optimizer has three paradigms: direct optimization, tool-augmented optimization, and tool-creating optimization. Direct optimization uses iterative prompting and heuristic generation to navigate solution spaces. Tool-augmented optimization translates natural language problems into formal specifications and orchestrates external solvers. Tool-creating optimization goes further, using LLMs to discover reusable algorithms or heuristics that can be deployed at zero marginal LLM cost. We describe current performance frontiers based on the benchmarks from the literature. We identify the critical reasoning gap in current architectures and argue for trade-offs between the future potential of direct optimization and the auditability of tool-augmented optimization. Even future, more powerful models might opt for tool-making to improve operational efficiency for repetitive families of problems.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-12

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Authors:
Yu Ying Chiu↗Michael S. Lee↗Rachel Calcott↗Brandon Handoko↗Paul de Font-Reaulx↗Rapha\"el Milli\`ere↗Paula Rodriguez↗Chen Bo Calvin Zhang↗Ziwen Han↗Udari Madhushani Sehwag↗Yash Maurya↗Christina Q Knight↗…

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models' abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

Read & Discuss → View Source →
09.
medRxiv (Medicine) 2026-06-15

Entity-Aware Generation of Synthetic Clinical Progress Notes for Prostate Cancer using Large Language Model

Authors:
Rey-Blanes↗Veredas-Morente↗Moreno-Barea↗F. J↗Veredas↗

Objectives: This study investigates large language models (LLMs) for clinical entity projection across substantial textual transformation. Specifically, we evaluate whether entities annotated in Spanish prostate cancer case reports can be preserved and explicitly projected when the source narratives are transformed into hospital-style clinical progress notes. Entity projection is treated as a generation-driven task, allowing paraphrase, condensation and narrative reorganisation, providing that clinically relevant entities remain recoverable as structured annotations. Methods: A corpus of 109 Spanish prostate cancer case reports was annotated using a silver-standard pipeline combining Spanish biomedical named-entity recognition with rule-based prostate-specific antigen (PSA) and Gleason extractors. The resulting silver-standard annotations were validated on a subset of generated notes against a gold-standard consensus produced by medical experts in prostate cancer. Four LLMs were evaluated for note generation and entity projection: GPT-5.4 Nano, Qwen 3.5:35B-A3B, GLM5 and Claude Sonnet 4.6. Entity-to-Entity (E2E) generation used XML-annotated cases as RAG-supported input, whereas Text-to-Entity (T2E) generation required models to generate and annotate notes directly from plain text cases. Zero-shot and few-shot prompting were tested. Projection quality was measured using precision, recall and F1-score, and complemented by LLM-as-a-judge evaluation using Kimi K2.6. Results: E2E consistently outperformed T2E, indicating that explicit entity-enriched in- put substantially facilitates entity preservation and localisation. GLM5 achieved the best E2E zero-shot result (F1 = 0.915), followed by Claude Sonnet 4.6 (F1 = 0.896). In T2E, few-shot prompting improved performance, with Claude Sonnet 4.6 reaching the highest score (F1 =0.718). Age, Gleason, Disease, Procedure, Duration and negation-related entities were robustly projected, whereas PSA and Dose showed less stable behaviour. Conclusion: LLMs can generate clinically plausible synthetic prostate cancer evolution notes while preserving a substantial proportion of source entities, particularly when explicit semantic annotations are provided as input. However, the lower and more variable performance observed in T2E highlights the difficulty of jointly generating clinical narratives and projecting entities without source-side information, especially for numerical and measure-related entities.

Read & Discuss → View Source →
10.
PLOS Medicine 2026-06-24

Cardiovascular outcomes and safety associated with statin therapy for primary prevention in older adults with type 2 diabetes: A target trial emulation study

Authors:
Linda Chan↗

by Linda Chan, Wanchun Xu, Esther W. Y. Chan, Eric Yuk Fai Wan Background There is limited evidence on the use of statins for primary prevention of cardiovascular disease (CVD) in older adults with type 2 diabetes due to underrepresentation of this population in randomized controlled trials (RCTs). We aimed to determine the effectiveness and safety of statin therapy for primary CVD prevention among type 2 diabetes patients aged ≥75 years. Methods and findings In this cohort study, territory-wide electronic health records (EHRs) from the Hospital Authority Clinical Management System in Hong Kong were used to emulate a sequence of nested target trials. Eligible patients were included in a rolling basis in each calendar month from January 2009 to December 2015, and thus we emulated 84 ‘nested monthly trials’. In each monthly trial, all type 2 diabetes patients aged ≥60 years with elevated low-density lipoprotein cholesterol (≥2.6 mmol/L) in the baseline calendar month were included; patients with a history of type 1 diabetes, CVDs, cancers, muscle-related disorders, or liver dysfunction were excluded from analysis. Eligible individuals were classified into statin initiators or noninitiators based on whether they initiated statin therapy at the time of enrollment. They were categorized into various age groups (60–74, 75–84, ≥85 years) for analysis, with those aged 60–74 years forming a benchmark group to test the validity of the emulated target trial. Patients were followed up until the outcome of interest, death, or the administrative end (December 2018), whichever occurred first. We estimated hazard ratios (HRs) comparing statin use versus nonuse for CVDs, all-cause mortality, muscle-related adverse events (AEs), and liver dysfunction using pooled logistic models, with inverse probability weighting to adjust for time-varying confounders related to treatment adherence, under the assumption of no unmeasured confounding. Propensity score matching was performed on eligible person-trials at baseline, incorporating demographic characteristics, clinical and laboratory parameters, comorbidities, medication history, and healthcare utilization as matching variables. Among 30,804 matched person-trials aged 75–84 years, a significant reduction in the incidence of CVDs (HR 0.69 (95% CI [0.65, 0.75]; p 

Read & Discuss → View Source →
11.
medRxiv (Medicine) 2026-06-24

Genetically Proxied Interleukin-6 Inhibition and Cancer Risk: A Multi-Ancestry Drug-Target Mendelian Randomization Study of Hepatocellular Carcinoma and Colorectal Cancer

Authors:
Ranjha↗M. M. A↗Munir↗

Background: Interleukin-6 (IL-6) signalling drives chronic inflammation and is therapeutically targeted by tocilizumab, an approved IL-6 receptor inhibitor. Whether genetically proxied lifelong IL-6 inhibition causally influences the risk of hepatocellular carcinoma (HCC) or colorectal cancer (CRC) remains unanswered. Prior single-variant estimates from pooled observational data are methodologically limited and may reflect confounding. Methods: A two-sample drug-target Mendelian randomization (MR) study was conducted. Four independent cis-acting protein quantitative trait loci (pQTL) variants within the IL6 and IL6R gene loci (rs2228145, rs4129267, rs7529229, rs1800795) were selected as genetic instruments , with F-statistics ranging from 32.3 to 120.5, confirming instrument strength. Outcome data were obtained from four independent genome-wide association studies: HCC from BioBank Japan (BBJ; 1,866 cases, 195,745 controls), HCC from FinnGen Release 10 (674 cases, 218,118 controls), CRC from a European meta-analysis (19,948 cases, 12,124 controls), and CRC from BBJ (7,062 cases, 195,745 controls). Causal estimates were derived using inverse variance weighted (IVW) regression as the primary method, with MR-Egger and weighted median analyses as sensitivity methods. Cochran Q statistics assessed heterogeneity and MR-Egger intercept testing assessed directional pleiotropy. Results: Genetically proxied IL-6 inhibition showed no significant causal effect on HCC risk in East Asian populations (IVW odds ratio [OR] 0.997, 95% confidence interval [CI] 0.903 to 1.101, p=0.953) or European populations (IVW OR 0.984, 95% CI 0.802 to 1.208, p=0.880). Similarly, no causal effect was observed on CRC risk in European populations (IVW OR 1.015, 95% CI 0.957 to 1.075, p=0.623) or East Asian populations (IVW OR 0.999, 95% CI 0.948 to 1.052, p=0.971). Sensitivity analyses confirmed the absence of directional pleiotropy and heterogeneity across all four analyses. Leave-one-out analyses demonstrated that no single instrument drove the null findings. Conclusions: Genetically proxied IL-6 receptor inhibition, modelling the therapeutic effect of tocilizumab, showed no causal effect on HCC or CRC risk across four independent cohorts and two ancestries. These findings do not support a role for IL-6 pathway inhibition in the prevention of these cancers and provide reassuring genetic safety evidence regarding cancer risk in patients receiving tocilizumab. Larger HCC-specific GWAS are needed to definitively evaluate modest effects in this cancer type.

Read & Discuss → View Source →
12.
arXiv (CS.AI) 2026-06-12

Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media

Authors:
Chuang Li↗Lixuan Wang↗Yuqi Chen↗Ze Hong↗

arXiv:2606.12418v1 Announce Type: cross Abstract: The rapid proliferation of large language models (LLMs) has produced a striking cultural practice: using conversational AI for divination. This paper offers one of the first systematic studies of LLM-mediated divination in the context of Xuanxue, an internet-native umbrella term for mystical and spiritual practices on Chinese social media. Using a mixed-methods design, we analyze 23000+ posts and comments from Xiaohongshu and conduct 32 semi-structured interviews with users and professional diviners. Users primarily consult LLMs about pragmatic concerns - romantic relationships, careers, exams, and in-game gacha draws - via two intersecting pathways: trend-driven curiosity enabled by viral visibility and zero-cost access, and event-driven anxiety under conditions of uncertainty. A defining feature is collaborative prompt refinement, which turns users into active prompt engineers. Among commenters expressing a clear stance, perceived efficacy skews positive, with "accuracy" often justified through biographical fit and retrospective confirmation, consistent with Barnum and confirmation bias. Users also develop verification practices such as repeated trials and cross-model comparison. Professional diviners, by contrast, portray LLMs as lacking the "spiritual power" required for genuine divination, reflecting both ontological commitments and economic boundary-work. We also show how participants navigate tensions between scientific and metaphysical frames when interpreting AI-generated readings. Situating these findings in anthropological and cognitive-evolutionary theories of divination, we argue that LLM divination preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape how divinatory authority is constructed and evaluated.

Read & Discuss → View Source →
13.
arXiv (CS.AI) 2026-06-18

CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System

Authors:
Marco Becattini↗Niccol\`o Caselli↗Matteo Minin↗Roberto Verdecchia↗Enrico Vicario↗

arXiv:2606.18976v1 Announce Type: cross Abstract: Automated assessment in software engineering education has advanced significantly for code grading and essay scoring. However, reviewing software architecture deliverables, which requires analyzing structural completeness and requirements traceability, has not yet been fully automated. Applying Large Language Models (LLMs) to this task requires robust architectures to ensure technical feedback is accurate and reliable for students. This paper presents CAPRA (Configurable Architecture Proficiency Report Assessment), a multi-agent LLM system that analyzes software architecture deliverables to generate personalized, template-compliant LaTeX feedback. As a core design choice, CAPRA coordinates multiple specialized agents and employs a Python-based microservice for multi-modal document extraction, utilizing PyMuPDF and vision-enabled LLMs (specifically gpt-4o) to parse text and UML diagrams. To ensure educational reliability and mitigate hallucinations, CAPRA introduces a deterministic Evidence Anchoring step using fuzzy matching via normalized Levenshtein distance, along with a ConsistencyManager agent that cross-verifies, deduplicates, and merges findings. System performance is assessed using a structured eight-criterion binary evaluation taxonomy covering: (i) extraction completeness, (ii) feature validation, (iii) issue grounding and severity detection, (iv) recommendation specificity and traceability, and (v) template and tone compliance. A preliminary empirical evaluation on 10 student reports shows that CAPRA satisfied 88.8% of the evaluated criteria under a strict two-rater aggregation rule, achieved moderate inter-rater agreement with human evaluators (kappa = 0.582), and processed each report in slightly over 4 minutes. While these results support the viability of LLM-supported architectural feedback, human oversight remains essential for subjective assessment dimensions.

Read & Discuss → View Source →
14.
arXiv (CS.CL) 2026-06-19

TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment

Authors:
Xiaochen Zheng↗Zhiwen Jiang↗David Tokar↗Yexiang Cheng↗Alvaro Serra↗Melanie Guerard↗Klas Hatje↗Tatyana Doktorova↗

Target Safety Assessment (TSA) requires systematic integration of genetic, transcriptomic, target homology, pharmacological, and clinical data to evaluate potential safety liabilities of therapeutic targets. This process is labor-intensive and expert-dependent, posing challenges in scalability and reproducibility. We present TSAssistant, a human-in-the-loop multi-agent framework that decomposes TSA report generation into a workflow of specialized subagents: Research Subagents that each ground and cite a single TSA domain, and Synthesis Subagents that integrate findings across domains. Subagents retrieve and synthesize evidence from curated biomedical sources through standardized tool interfaces and produce individually citable, evidence-grounded sections, with behavior shaped by a hierarchical instruction architecture that separates coordination logic from domain expertise and user intent. To complement these soft constraints, programmatic execution hooks and persistent memory stores enforce hard constraints across the workflow, while an interactive refinement loop allows experts to review and revise individual sections with full conversational context preserved across iterations. Rather than a single holistic comparison, we decompose report quality into reproducibility, evidential grounding, task-level accuracy, and controllability under expert oversight, finding high reproducibility and grounding, substantial agreement with the human reference, and net-positive expert-driven refinement.

Read & Discuss → View Source →
15.
arXiv (math.PR) 2026-06-24

Perron–Frobenius theorem for a general tree-valued growth-fragmentation-isolation process

Authors:
Chenlin Gu↗Mingyuan Shen↗Ronghang Zhang↗

arXiv:2606.24599v1 Announce Type: new Abstract: A general tree-valued dynamics is considered in continuous time: new vertices are added, and the percolation happens on the links, and the connected components can be frozen. The model is an infinite-type branching process. The main result establishes the Perron–Frobenius type theorem on this model, which extends the previous work [Ann. Appl. Probab. 33 (6B) 5233 - 5278]. The proof does not rely on any property of the uniform random recursive tree.

Read & Discuss → View Source →
16.
arXiv (CS.CV) 2026-06-16

HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics

Authors:
Masatoshi Tateno↗Gido Kato↗Hirokatsu Kataoka↗Yoichi Sato↗Takuma Yagi↗

Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks focused either on manipulation or on the resulting effects at a coarse level, lacking fine-grained spatio-temporal reasoning to capture the underlying dynamics in HOI. We introduce HanDyVQA, a fine-grained video question-answering benchmark that comprehensively covers both the manipulation and effect aspects of HOI. HanDyVQA comprises six complementary question types (Action, Process, Objects, Location, State Change, and Object Parts), totalling 11.1K multiple-choice QA pairs. Collected QA pairs recognizing manipulation styles, hand/object motions, and part-level state changes. HanDyVQA also includes 10.3K segmentation masks for Objects and Object Parts questions, enabling the evaluation of object/part-level reasoning in video object segmentation. We evaluated recent video foundation models on our benchmark and found that even the best-performing model, Gemini-2.5-Pro, reached only 73% average accuracy, which is far from human performance (97%). Further analysis shows the remaining challenges in spatial relationship, motion, and part-level geometric understanding. We also found that integrating explicit HOI-related cues into visual features improves performance, offering insights for developing future models with a deeper understanding of HOI dynamics.

Read & Discuss → View Source →
17.
arXiv (quant-ph) 2026-06-25

Pauli stabilizer formalism for topological quantum field theories and generalized statistics

Authors:
Yitao Feng↗Hanyu Xue↗Ryohei Kobayashi↗Po-Shen Hsin↗Yu-An Chen↗

arXiv:2601.00064v3 Announce Type: replace Abstract: Topological quantum field theory (TQFT) provides a unifying framework for describing topological phases of matter and for constructing quantum error-correcting codes, playing a central role across high-energy physics, condensed matter, and quantum information. A central challenge is to formulate topological order on lattices and to extract the properties of topological excitations from microscopic Hamiltonians. In this work, we construct new classes of lattice gauge theories as Pauli stabilizer models, realizing a wide range of TQFTs in general dimensions. We develop a lattice description of extended excitations and systematically determine their generalized statistics. Our main example is the (4+1)D fermionic-loop toric code, obtained by condensing the $e^2m^2$-loop in the (4+1)D $\mathbb Z_4$ toric code. We show that the loop excitation exhibits fermionic loop statistics: the 24-step loop-flipping process yields a phase of $-1$. Our Pauli stabilizer models realize all twisted 2-form gauge theories in (4+1)D, the higher-form Dijkgraaf-Witten TQFT classified by $H^5(B^2G,U(1))$. Beyond (4+1)D, the fermionic-loop toric codes form a family of $\mathbb Z_2$ topological orders in arbitrary dimensions, realized as explicit Pauli stabilizer codes using $\mathbb Z_4$ qudits. Finally, we develop a Pauli-based framework that defines generalized statistics for extended excitations in any dimension, yielding computable lattice unitary processes to detect nontrivial statistics. For example, we propose anyonic membrane statistics in (6+1)D, as well as fermionic membrane and volume statistics in arbitrary dimensions. We construct new families of $\mathbb Z_2$ topological orders: the fermionic-membrane toric code and the fermionic-volume toric code. In addition, we demonstrate that $p$-dimensional excitations in $2p+2$ spatial dimensions can support anyonic $p$-brane statistics for only even $p$.

Read & Discuss → View Source →
18.
arXiv (CS.CL) 2026-06-16

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

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

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

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-24

ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

Authors:
Zhentao Guo↗Chen Duan↗Tongkun Guan↗Zining Wang↗Kai Zhou↗Pengfei Yan↗

Despite remarkable progress in multimodal understanding, current MLLMs still exhibit limitations in video text understanding, particularly when semantics emerge through the integration of temporally distributed textual cues across multiple frames. This perception challenge fundamentally differs from static image text understanding, yet existing datasets fail to capture: the vast majority of questions remain answerable from single frames, inadequately reflecting real-world video text comprehension demands. To address this, we present ViTexQA, a large-scale video-text QA dataset, and FrameThinker for robust multi-frame temporal reasoning. We build ViTexQA via a quality-controlled Chain-of-Thought (CoT) annotation pipeline boosted with temporal constraints; all its QA pairs demand cross-frame text fusion to solve, enforcing true temporal reliance. FrameThinker adopts two-stage training for explicit temporal modeling: CoT-Guided Supervised Fine-Tuning (SFT) generates frame-aware reasoning chains, followed by Temporally-grounded Reinforcement Learning (RL) optimized with multi-frame coherence rewards. Evaluations show our method outperforms SOTA baselines on ViTexQA, lifting ROUGE-L by 6.3%.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-18

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning

Authors:
Ruoran Xu↗Haoyu Cheng↗Bin Dong↗Qiufeng Wang↗

Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry while usually fail in solid geometry due to 3D spatial diagrams and complex reasoning. To bridge this gap, we introduce Hilbert-Geo, the first unified formal language framework for solid geometry, including an extensive predicate library and a dedicated theorem bank. Based on this framework, we propose a Parse2Reason method containing two steps of first parsing then reasoning. In the parsing step, we utilize conditional description language (CDL), a formalized language composed of predicates specifically designed to construct geometric conditions, to represent both problem description (natural text) and solid diagrams (visual image). In the reasoning step, we leverage those formal CDL and the theorem bank to perform relational inference and algebraic computation, generating strictly correct, verifiable, and human-readable reasoning processes. Notably, our proposed Hilbert-Geo is also applicable to plane geometry. To advance geometric reasoning, we curate two expert-annotated dataset SolidFGeo2k and PlaneFGeo3k, which are furnished with geometric formal language annotations, solutions and answers. Extensive experiments show that our proposed method achieves the state-of-the-art (SOTA) performance 77.3% in SolidFGeo2k and 84.1% in MathVerse-Solid (one small subset in MathVerse dedicated to solid geometry), substantially outperforming leading MLLMs, such as Gemini-2.5-pro (54.2% on SolidFGeo2k) and GPT-5 (62.9% on MathVerse-Solid). In addition, our method achieves the SOTA accuracy 80.2% in PlaneFGeo3k, demonstrating the generality of the Hilbert-Geo in geometric reasoning. Our code and datasets are released at https://github.com/PremiLab-Math/Hilbert-Geo.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-11

MedCTA: A Benchmark for Clinical Tool Agents

Authors:
Tajamul Ashraf↗Hyewon Jeong↗Fida Mohammad Thoker↗Bernard Ghanem↗

To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Existing benchmarks largely evaluate isolated perception or single-turn question answering, and therefore provide limited visibility into failures of planning, tool recruitment, and rollout reliability. We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks grounded in realistic multimodal clinical inputs, including radiology images, pathology slides, and reports. MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools, and supports process-aware evaluation of tool selection, argument validity, execution stability, trajectory fidelity, and outcome quality. We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use: autonomous rollouts are dominated by protocol failures, premature stopping, and incorrect tool recruitment, while gold-standard tool routing yields large but still incomplete gains. These results show that strong backbone perception does not translate into reliable agentic behavior in clinical settings. MedCTA provides a rigorous testbed for auditing, diagnosing, and advancing trustworthy medical AI agents. The dataset and evaluation suite are available at https://ivul-kaust.github.io/MedCTA/

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-24

Random coloured digraphs defined by a Markov logic network

Authors:
Yasmin Tousinejad↗Vera Koponen↗

arXiv:2606.23715v1 Announce Type: cross Abstract: A Markov Logic Network (MLN) is a probabilistic relational model used in Statistical Relational Artificial Intelligence for defining a probability distribution on the set of possible worlds with domain $D$ for an arbitrary finite domain $D$. An MLN consists of soft constraints with associated weights which are nonnegative real numbers. In this study we consider a language speaking about a property $P(x)$ and a relation $R(x, y)$. We consider an MLN for which every Boolean combination of $P(x)$ and $R(x, y)$ is a soft constraint (with associated weight). Let $n$ denote the size (cardinality) of the domain. We show that, for every choice of weights, if the weights are scaled by $1/n$ then, for every first-order sentence $\varphi$, the probability that $\varphi$ holds tends to either 0 or 1 as $n \to \infty$; that is, a 0-1 law for first-order logic holds. Morover, the limit probability does not depend on the weights. If we instead use the standard semantics of MLNs, in the case of which the weights are not scaled, then the limit behaviour is more complicated and depends on the weights. With unscaled weights we get 7 qualitatively different cases which depend on the weights. In some cases we have a 0-1 law for first-order logic, in some cases not, but we may still have a convergence law. The influence of the weights on the asymptotic probability of a first-order sentence may be in the form of a sudden ``phase transition'' from one of the 7 cases to another. The presence of a convergence law has positive implications for inference on large domains.

Read & Discuss → View Source →
23.
PLOS Computational Biology 2026-06-24

The transcriptional gradient in negative-strand RNA viruses suggests a common RNA transcription mechanism

Authors:
Connor R. King↗

by Connor R. King, Casey-Tyler Berezin, Brian Munsky, Jean Peccoud Nonsegmented negative-strand RNA viruses (NNSV) are a diverse class of medically relevant viruses which display a conserved attenuation gradient in the transcription of their genomes. This gradient has been traditionally explained by the Stop-Start model which attributes attenuation to polymerase behavior at gene junctions. In this article, we evaluate an alternative explanation where the gradient arises from polymerase dynamics during transcription. We introduce the RNA Polymerase Association Mechanism (RAM) model, a coarse-grained stochastic framework that describes transcription using two parameters related to polymerase processivity and the ability of the polymerase to backtrack. The RAM model accurately reproduces transcriptional gradients across diverse NNSVs as well as in gene-shuffled VSV variants. Additionally, the inferred polymerase processivity appears correlated to the length of the viral genomes suggesting a conserved constraint on transcription across these viruses. While the RAM model does not account for all known molecular features of NNSV transcription, it provides a parsimonious and predictive framework for relating genome architecture and transcription. These results support the view that, in tandem with the traditional junction-centric mechanisms governing transcription, nonspecific attenuation mechanisms contribute to the NNSV transcriptional gradient and warrant closer inspection in future studies which could lead to better rational genome design in viral studies and biomedical applications.

Read & Discuss → View Source →
24.
arXiv (CS.CV) 2026-06-17

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

Authors:
Yanhao Wu↗Haoyang Zhang↗Fei He↗Rui Wu↗Yanhu Shan↗Congpei Qiu↗Liang Gao↗Wei Ke↗Tong Zhang↗

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.

Read & Discuss → View Source →
25.
arXiv (CS.LG) 2026-06-11

SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration

Authors:
Barsat Khadka↗Kawsher Roxy↗Md Rubel Ahmed↗

arXiv:2606.11348v1 Announce Type: new Abstract: Clock Tree Synthesis (CTS) is a computationally expensive stage in the physical design flow, requiring iterative EDA tool invocations to navigate a vast configuration space for optimal power, wirelength, and timing skew. Existing machine learning approaches require computationally expensive retraining or fine-tuning cycles to adapt to unseen macro architectures and are architecturally mismatched to the millions of evaluations demanded by exhaustive combinatorial search. We present SwiftCTS, a physics-informed surrogate framework that addresses both limitations simultaneously. By coupling lightweight, physics-grounded statistical features with gradient-boosted ensembles, SwiftCTS trains in under five seconds on a CPU and delivers sub-millisecond inference without GPU support. To handle out-of-distribution (OOD) designs without retraining or fine-tuning, we introduce a K-shot multiplicative calibration mechanism that anchors predictions to just one or two physical reference runs, reducing power prediction error from 24.5\% to 3.3\% and wirelength error from 56.6\% to under 1\% on unseen macros. Integrating this engine with an evolutionary optimizer, SwiftCTS evaluates 100,000 CTS configurations in under ten seconds, yielding Pareto-optimal frontiers that are physically validated within the OpenROAD flow. Closed-loop validation confirms prediction errors below 0.5\% for power and wirelength, and timing skew predictions within five picoseconds on an OOD benchmark, consistently outperforming default tool heuristics across all target metrics. Code publicly available at: \href{https://anonymous.4open.science/r/SwiftCTS-7E6E}{https://github.com/BarsatKhadka/SwiftCTS}

Read & Discuss → View Source →