❌

Normal view

Received — 10 September 2026 ⏭

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Weichen Dai · Rafael Medeiros Cabral · Ziyi Shou · Yan Cao · Xin Shen · Dongcai Lu · Yi Zhou
10 September 2026 at 12:00
arXiv:2609.10335v1 Announce Type: new Abstract: Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a Geometric Vision Parser, which translates diagrams into symbolic form, with a Symbolic Solver that performs formal deductions, thereby mitigating hallucinations and promoting interpretable reasoning. To enable rigorous evaluation, we curate a benchmark of challenging problems from the 2025 Chinese Zhongkao examinations, ensuring data novelty and testing deeper deductive skills. Experiments demonstrate that our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions.
Received — 27 May 2026 ⏭

LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zenghui Zhou · Man Li · Xiaoke Fang · Xinyi Zhou · Weibin Li · Zheng Zheng
26 May 2026 at 12:00
arXiv:2605.23965v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance on logical reasoning benchmarks, yet their reliability remains uncertain. Existing evaluations rely on static benchmarks, which fail to assess robustness under logically equivalent transformations and often overestimate reasoning capability. We propose LGMT (Logic-Grounded Metamorphic Testing), an oracle-free framework that leverages first-order logic (FOL) to evaluate LLM reasoning. By deriving metamorphic relations from formal logical equivalences, LGMT constructs semantically invariant test cases and detects reasoning defects through cross-case consistency checking. Experiments on six state-of-the-art LLMs show that LGMT exposes substantial hidden defects missed by traditional reference-based evaluations. We further find that models are particularly sensitive to symbol-level and conclusion-level variations, and that advanced prompting such as Few-shot CoT only partially mitigates these issues. These results suggest that LLM evaluation should move beyond isolated correctness toward robustness under logical invariance. LGMT provides a principled and scalable approach for diagnosing reasoning failures.

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bingyu Yan · Xiaoming Zhang · Jinyu Hou · Chaozhuo Li · Ziyi Zhou · Yiming Hei · Litian Zhang
26 May 2026 at 12:00
arXiv:2605.25389v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools, the implicit trust in tool outputs creates a critical attack surface. Existing tool attacks are limited by domain specificity or fixed and static templates. To address these challenges, we propose Evo-Attacker, which formulates the tool attack as a self-evolving, memory-augmented reinforcement learning process. Evo-Attacker constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns and strategize modifying interventions at critical moments. Furthermore, we introduce Attack-Flow GRPO to optimize intermediate reasoning steps via terminal outcomes, addressing the long-horizon credit assignment challenge. Comprehensive experiments demonstrate that Evo-Attacker consistently outperforms baselines, highlighting its generalization and evolutionary capabilities and the urgent need for defensive tool safeguards.

Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunqing Liu · Yi Zhou · Wenqi Fan
26 May 2026 at 12:00
arXiv:2605.25577v1 Announce Type: cross Abstract: The generation of accurate 3D molecular conformations is a pivotal challenge in computational chemistry and drug discovery. Recently, diffusion and flow matching models have achieved remarkable success. However, there is a critical misalignment between their mathematical formulation and the physical reality of molecules. Existing approaches predominantly treat molecules as unstructured point clouds in Cartesian space, overlooking the intrinsic hierarchical mechanics where bond lengths and bond angles are relatively stiff, whereas torsion angles constitute the dominant flexible degrees of freedom. This lack of manifold awareness forces models to relearn fundamental geometric constraints from scratch, often leading to physically implausible intermediate structures. To address this, we propose GO-Flow that aligns generative modeling with molecular geometry via manifold decomposition. Instead of forcing motion through Euclidean space, GO-Flow decomposes the generation process into three physically motivated subspaces: translation space with linear optimal transport, rotation space with geodesic flows on $SO(3)$, and conformation space with entropic optimal transport. This decomposition injects geometric inductive biases and makes the generative paths better aligned with molecular degrees of freedom. When combined with equivariant neural architectures, it encourages rotation-consistent generation and improves geometric validity. Extensive experiments on GEOM-Drugs and GEOM-QM9 demonstrate that GO-Flow achieves state-of-the-art generation quality. Notably, by learning straighter probability paths on the correct manifolds naturally, our method enables high-fidelity sampling with as few as 50 steps, effectively bridging the gap between structural precision and computational efficiency.

A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jia Huang · Joey Tianyi Zhou
26 May 2026 at 12:00
arXiv:2605.13850v2 Announce Type: replace Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on cognitive function -- what the agent does. Neither axis alone disambiguates architecturally distinct systems: the same Orchestrator-Workers topology can implement Plan-and-Execute, Hierarchical Delegation, or Adversarial Verification -- three patterns with fundamentally different failure modes and design trade-offs. We propose a two-dimensional classification that combines (1) a Cognitive Function axis with seven categories (Perception, Memory, Reasoning, Action, Reflection, Collaboration, Governance) and (2) an Execution Topology axis with six structural archetypes (Chain, Route, Parallel, Orchestrate, Loop, Hierarchy). The resulting 7x6 matrix identifies 28 named patterns, 15 with original names. We demonstrate orthogonality through systematic cross-axis analysis, define eight representative patterns in detail, and validate descriptive coverage across four real-world domains (financial lending, legal due diligence, network operations, healthcare triage). Cross-domain analysis yields five empirical laws of pattern selection governing the relationship between environmental constraints (time pressure, action authority, failure cost asymmetry, volume) and architectural choices. The framework provides a principled, framework-neutral, and model-agnostic vocabulary for AI agent architecture design.
Received — 8 April 2026 ⏭

From Paper to Program: A Multi-Stage LLM-Assisted Workflow for Accelerating Quantum Many-Body Algorithm Development

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Zhou
7 April 2026 at 12:00
arXiv:2604.04089v1 Announce Type: cross Abstract: Translating quantum many-body theory into scalable software traditionally requires months of effort. Zero-shot generation of tensor network algorithms by Large Language Models (LLMs) frequently fails due to spatial reasoning errors and memory bottlenecks. We resolve this using a multi-stage workflow that mimics a physics research group. By generating a mathematically rigorous LaTeX specification as an intermediate blueprint, we constrain the coding LLM to produce exact, matrix-free $\mathcal{O}(D^3)$ operations. We validate this approach by generating a Density-Matrix Renormalization Group (DMRG) engine that accurately captures the critical entanglement scaling of the Spin-$1/2$ Heisenberg model and the symmetry-protected topological (SPT) order of the Spin-$1$ AKLT model. Testing across 16 combinations of leading foundation models yielded a 100\% success rate. By compressing a months-long development cycle into under 24 hours ($\sim 14$ active hours), this framework offers a highly reproducible paradigm for accelerating computational physics research.

One Model for All: Multi-Objective Controllable Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiang He · Yucheng Yang · Tianyi Zhou · Meng Fang · Mykola Pechenizkiy · Setareh Maghsudi
7 April 2026 at 12:00
arXiv:2604.04497v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from human feedback (RLHF) mainly focuses on a fixed reward learned from average human ratings, which may weaken the adaptability and controllability of varying preferences. However, creating personalized LLMs requires aligning LLMs with individual human preferences, which is non-trivial due to the scarce data per user and the diversity of user preferences in multi-objective trade-offs, varying from emphasizing empathy in certain contexts to demanding efficiency and precision in others. Can we train one LLM to produce personalized outputs across different user preferences on the Pareto front? In this paper, we introduce Multi-Objective Control (MOC), which trains a single LLM to directly generate responses in the preference-defined regions of the Pareto front. Our approach introduces multi-objective optimization (MOO) principles into RLHF to train an LLM as a preference-conditioned policy network. We improve the computational efficiency of MOC by applying MOO at the policy level, enabling us to fine-tune a 7B-parameter model on a single A6000 GPU. Extensive experiments demonstrate the advantages of MOC over baselines in three aspects: (i) controllability of LLM outputs w.r.t. user preferences on the trade-off among multiple rewards; (ii) quality and diversity of LLM outputs, measured by the hyper-volume of multiple solutions achieved; and (iii) generalization to unseen preferences. These results highlight MOC's potential for real-world applications requiring scalable and customizable LLMs.
Received — 2 April 2026 ⏭

Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tao Chen · Kun Zhang · Qiong Wu · Xiao Chen · Chao Chang · Xiaoshuai Sun · Yiyi Zhou · Rongrong Ji
1 April 2026 at 12:00
arXiv:2603.29252v1 Announce Type: cross Abstract: Long video understanding is a key challenge that plagues the advancement of \emph{Multimodal Large language Models} (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed \emph{Flexible Memory} (\textbf{FlexMem}). In principle, FlexMem aims to mimic human behavior of video watching, \emph{i.e.}, continually watching video content and recalling the most relevant memory fragments to answer the question. In this way, FlexMem can help MLLMs achieve video understanding of infinite lengths, unlike previous methods that process all video information at once and have input upper-limit. Concretely, FlexMem first consider the visual KV caches as the memory sources, and realize the effective memory transfer and writing via a dual-pathway compression design. Afterwards, FlexMem also explores different memory reading strategies for the diverse video understanding tasks, including the popular streaming one. To validate FlexMem, we apply it to two popular video-MLLMs, and conduct extensive experiments on five long video and one streaming video task. The experimental results show that on \textbf{a single 3090 GPU}, our FlexMem can achieve obvious improvements than existing efficient video understanding methods and process more than \textbf{1k frames}, which also helps the base MLLMs achieve comparable or even better performance than SOTA MLLMs on some benchmarks, \emph{e.g.} , GPT-4o and Gemini-1.5 Pro.

Generative AI in Action: Field Experimental Evidence from Alibaba's Customer Service Operations

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiao Ni · Yiwei Wang · Tianjun Feng · Lauren Xiaoyan Lu · Yitong Wang · Congyi Zhou
1 April 2026 at 12:00
arXiv:2603.29888v1 Announce Type: cross Abstract: In collaboration with Alibaba, this study leverages a large-scale field experiment to assess the impact of a generative AI assistant on worker performance in e-commerce after-sales service. Human agents providing digital chat support were randomly assigned with access to a gen AI assistant that offered two core functions: diagnosis of customer issues and solution proposals, presented as text messages. Agents retained discretion to adopt, modify, or disregard AI-generated messages. To evaluate gen AI's impact, we estimate both the intention-to-treat (ITT) effect of gen AI access and the local average treatment effect (LATE) of gen AI usage. Results show that gen AI significantly improved service speed, measured by issue identification time and chat duration. Gen AI also improved subjective service quality reflected in customer ratings and dissatisfaction rates, but it had no significant effect on objective service quality indicated by customer retrial rates. The performance improvements stemmed not only from automation but also from changes in the dynamics of agent-customer interactions: agent communication became more informative and efficient, while customers experienced reduced communication burdens. Low performers achieved the greatest improvements in both service speed and quality, narrowing the performance gap. In contrast, top-performing agents showed little improvement in service speed but experienced declines in both subjective and objective service quality. Evidence suggests that this decline results from increased multitasking tendency, proxied by longer shift-away times across concurrent chats, which slowed customer responses and raised abandonment and retrial rates. These findings suggest that gen AI reshapes work, demanding tailored deployment strategies.

Proposed Role of Circadian Clock Genes in Pathogenesis of HCC: Molecular Subtyping and Characterization

✇Omics in Hepatocellular
By: Zhikui Lu · Yi Zhou · Jian Luo · Zhicheng Liu · Zhenyu Xiao
28 March 2026 at 18:00

Biomedicines. 2026 Mar 12;14(3):645. doi: 10.3390/biomedicines14030645.

ABSTRACT

Background: Hepatocellular carcinoma (HCC) stands as a prevalent global health issue with increasing incidence and mortality rates. Hepatocellular carcinoma (HCC) exhibits profound molecular and clinical heterogeneity, which limits the effectiveness of current therapeutic strategies. Circadian rhythm disruption has been implicated in metabolic reprogramming, proliferation, and immune modulation in cancer, but its role in shaping HCC heterogeneity remains poorly defined. Methods: Four public HCC transcriptomic cohorts (TCGA-LIHC, CHCC, LIRI, LICA) were integrated using RMA normalization and ComBat for batch correction. Consensus clustering based on 31 core circadian clock genes (CCGs) identified robust molecular subtypes. Multi-omics characterization-including genomic alterations, pathway activity (GSEA/GSVA), immune microenvironment profiling (CIBERSORT, EPIC, MCP-counter, xCell), and drug-sensitivity prediction (pRRophetic/oncoPredict)-was performed to delineate subtype-specific biological properties. A nine-gene CCG-based RiskScore model was constructed using LASSO Cox regression to internally validate subtype robustness and intra-subtype risk stratification. Results: Using consensus clustering of 31 core CCGs in TCGA-LIHC and three independent validation cohorts (CHCC, LIRI, LICA), we identified three reproducible subtypes-Cluster-1 (metabolic-quiescent), Cluster-2 (transition-intermediate), and Cluster-3 (proliferation-inflammatory)-which were recapitulated across cohorts and showed distinct overall survival (Cluster-3 worst; log-rank p values significant across datasets). Multi-omic characterization revealed that Cluster-3 exhibits the highest tumor mutational burden and CNV burden with enrichment of TP53/AXIN1/TERT alterations, strong activation of cell-cycle, E2F, and G2M programs, and an immune-hot yet immunosuppressed microenvironment enriched for TAMs, Tregs and MDSCs. By contrast, Cluster-1 shows relative genomic stability, dominant hepatic metabolic signatures (fatty-acid oxidation, bile-acid and xenobiotic metabolism) and an immune-cold phenotype. Single-cell mapping linked ALAS1 expression to malignant hepatocytes predominating in Cluster-1, whereas NONO and CSNK1D localized to stromal (CAFs/TECs) and both malignant/immune compartments respectively in Cluster-3, providing a cellular mechanism for subtype-specific metabolism, angiogenesis and immune modulation. Finally, a nine-gene CCG-based RiskScore validated prognostic stratification and drug-sensitivity predictions indicated subtype-specific therapeutic vulnerabilities (notably increased predicted TKI sensitivity in Cluster-3). Conclusion: In conclusion, this study proposes a robust circadian rhythm-based molecular classification of hepatocellular carcinoma, revealing three biologically and clinically distinct subtypes characterized by divergent genomic alterations, metabolic programs, immune microenvironment states, and prognostic patterns. By integrating bulk and single-cell transcriptomic data, we identify subtype-specific roles of key circadian regulators-including ALAS1, NONO, and CSNK1D-in shaping tumor metabolism, proliferation, stromal remodeling, and immune suppression. These findings highlight circadian dysregulation as a potential upstream factor associated with HCC heterogeneity and provide a conceptual framework for developing subtype-tailored mechanistic studies and circadian-informed therapeutic strategies.

PMID:41898292 | PMC:PMC13024568 | DOI:10.3390/biomedicines14030645

Received — 26 March 2026 ⏭

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shaobo Ju · Baiyang Song · Tao Chen · Jiapeng Zhang · Qiong Wu · Chao Chang · HuaiXi Wang · Yiyi Zhou · Rongrong Ji
25 March 2026 at 12:00
arXiv:2603.22911v1 Announce Type: cross Abstract: Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of high-ratio token compression. We attribute this shortcoming to the insufficient modeling of temporal and continual video content, and propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune, which achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling. In practice, ForestPrune construct token forests across video frames based on the semantic, spatial and temporal constraints, making an overall comprehension of videos. Afterwards, ForestPrune evaluates the importance of token trees and nodes based on tree depth and node roles, thereby obtaining a globally optimal pruning decision. To validate ForestPrune, we apply it to two representative video MLLMs, namely LLaVA-Video and LLaVA-OneVision, and conduct extensive experiments on a bunch of video benchmarks. The experimental results not only show the great effectiveness for video MLLMs, e.g., retaining 95.8% average accuracy while reducing 90% tokens for LLaVA-OneVision, but also show its superior performance and efficiency than the compared token compression methods, e.g., +10.1% accuracy on MLVU and -81.4% pruning time than FrameFusion on LLaVA-Video.

Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dadi Guo · Tianyi Zhou · Dongrui Liu · Chen Qian · Qihan Ren · Shuai Shao · Zhiyuan Fan · Yi R. Fung · Kun Wang · Linfeng Zhang · Jing Shao
25 March 2026 at 12:00
arXiv:2510.00415v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed agents, making it difficult to meet the demands for evaluating agent abilities. To address this problem, we propose the Trajectory-based Validated-by-Reproducing Agent-benchmark Complexity Evolution (TRACE) framework. This framework takes an original task from an existing benchmark and encourages agents to freely explore and evolve it into a new task with higher difficulty while recording validatable agent trajectories. The framework proceeds in three stages: (1) evolutionary proposal mining, which provides task evolution proposals through preliminary exploration and divergent thinking; (2) problem formation and free exploration, where proposals are conceptualized into feasible problem candidates and the agents then explore them freely while recording their execution trajectories; and (3) multi-level validation, which ensures that the evolved tasks are accompanied by validatable and reproducible trajectories. Experiments on the GAIA benchmark demonstrate that the TRACE framework consistently enhances task complexity while improving the reliability of correctness through validatable execution trajectories. In addition, our framework can successfully adapt to and improve reasoning datasets represented by AIME-2024. This work marks a paradigm shift from static, manually curated benchmarks to dynamic, self-evolving evaluation systems, providing a sustainable and challenging runway for agent development
Received — 11 March 2026 ⏭

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haodong Li · Chunmei Qing · Huanyu Zhang · Dongzhi Jiang · Yihang Zou · Hongbo Peng · Dingming Li · Yuhong Dai · ZePeng Lin · Juanxi Tian · Yi Zhou · Siqi Dai · Jingwei Wu
10 March 2026 at 12:00
arXiv:2603.08652v1 Announce Type: new Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene, which is then executed in a sandboxed environment to render a deterministic draft image. The model subsequently refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of +68.83%, +54.8%, and +41.23% over direct generation, while also outperforming other generation methods empowered by CoT. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation. The code is available at: https://github.com/micky-li-hd/CoCo
Received — 5 March 2026 ⏭

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qinsi Wang · Bo Liu · Tianyi Zhou · Jing Shi · Yueqian Lin · Yiran Chen · Hai Helen Li · Kun Wan · Wentian Zhao
5 March 2026 at 13:00
arXiv:2509.25541v2 Announce Type: replace-cross Abstract: Although reinforcement learning (RL) has emerged as a promising approach for improving vision-language models (VLMs) and multimodal large language models (MLLMs), current methods rely heavily on manually curated datasets and costly human verification, which limits scalable self-improvement in multimodal systems. To address this challenge, we propose Vision-Zero, a label-free, domain-agnostic multi-agent self-play framework for self-evolving VLMs through competitive visual games generated from arbitrary image inputs. Specifically, Vision-Zero encompasses three main attributes: (1) Strategic Self-Play Framework: Vision-Zero trains VLMs in "Who Is the Spy"-style games, where the models engage in strategic reasoning and actions across multiple roles. Through interactive gameplay, models autonomously generate their training data without human annotation. (2) Gameplay from Arbitrary Images: Unlike existing gamified frameworks, Vision-Zero can generate games from arbitrary images, thereby enhancing the model's reasoning ability across diverse domains and showing strong generalization to different tasks. We demonstrate this versatility using three distinct types of image datasets: CLEVR-based synthetic scenes, charts, and real-world images. (3) Sustainable Performance Gain: We introduce Iterative Self-Play Policy Optimization (Iterative-SPO), a novel training algorithm that alternates between Self-Play and reinforcement learning with verifiable rewards (RLVR), mitigating the performance plateau often seen in self-play-only training and achieving sustained long-term improvements. Despite using label-free data, Vision-Zero achieves state-of-the-art performance on reasoning, chart question answering, and vision-centric understanding tasks, surpassing other annotation-based methods. Models and code have been released at https://github.com/wangqinsi1/Vision-Zero.

RubricBench: Aligning Model-Generated Rubrics with Human Standards

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiyuan Zhang · Junyi Zhou · Yufei Wang · Fuyuan Lyu · Yidong Ming · Can Xu · Qingfeng Sun · Kai Zheng · Peng Kang · Xue Liu · Chen Ma
4 March 2026 at 13:00
arXiv:2603.01562v2 Announce Type: replace Abstract: As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing benchmarks lack both the discriminative complexity and the ground-truth rubric annotations required for rigorous analysis. To bridge this gap, we introduce RubricBench, a curated benchmark with 1,147 pairwise comparisons specifically designed to assess the reliability of rubric-based evaluation. Our construction employs a multi-dimensional filtration pipeline to target hard samples featuring nuanced input complexity and misleading surface bias, augmenting each with expert-annotated, atomic rubrics derived strictly from instructions. Comprehensive experiments reveal a substantial capability gap between human-annotated and model-generated rubrics, indicating that even state-of-the-art models struggle to autonomously specify valid evaluation criteria, lagging considerably behind human-guided performance.
Received — 25 February 2026 ⏭

TxRay: Agentic Postmortem of Live Blockchain Attacks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziyue Wang · Jiangshan Yu · Kaihua Qin · Dawn Song · Arthur Gervais · Liyi Zhou
24 February 2026 at 13:00
arXiv:2602.01317v5 Announce Type: replace-cross Abstract: Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exposes pools of value controlled by code. Within five years, the DeFi ecosystem has lost over 15.75B USD to reported exploits. Many exploits arise from permissionless opportunities that any participant can trigger using only public state and standard interfaces, which we call Anyone-Can-Take (ACT) opportunities. Despite on-chain transparency, postmortem analysis remains slow and manual: investigations start from limited evidence, sometimes only a single transaction hash, and must reconstruct the exploit lifecycle by recovering related transactions, contract code, and state dependencies. We present TxRay, a Large Language Model (LLM) agentic postmortem system that uses tool calls to reconstruct live ACT attacks from limited evidence. Starting from one or more seed transactions, TxRay recovers the exploit lifecycle, derives an evidence-backed root cause, and generates a runnable, self-contained Proof of Concept (PoC) that deterministically reproduces the incident. TxRay self-checks postmortems by encoding incident-specific semantic oracles as executable assertions. To evaluate PoC correctness and quality, we develop PoCEvaluator, an independent agentic execution-and-review evaluator. On 114 incidents from DeFiHackLabs, TxRay produces an expert-aligned root cause and an executable PoC for 105 incidents, achieving 92.11% end-to-end reproduction. Under PoCEvaluator, 98.1% of TxRay PoCs avoid hard-coding attacker addresses, a +22.9pp lift over DeFiHackLabs. In a live deployment, TxRay delivers validated root causes in 40 minutes and PoCs in 59 minutes at median latency. TxRay's oracle-validated PoCs enable attack imitation, improving coverage by 15.6% and 65.5% over STING and APE.
Received — 17 February 2026 ⏭

Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ming Li · Xirui Li · Tianyi Zhou
17 February 2026 at 13:00
arXiv:2602.14299v1 Announce Type: cross Abstract: As large language model agents increasingly populate networked environments, a fundamental question arises: do artificial intelligence (AI) agent societies undergo convergence dynamics similar to human social systems? Lately, Moltbook approximates a plausible future scenario in which autonomous agents participate in an open-ended, continuously evolving online society. We present the first large-scale systemic diagnosis of this AI agent society. Beyond static observation, we introduce a quantitative diagnostic framework for dynamic evolution in AI agent societies, measuring semantic stabilization, lexical turnover, individual inertia, influence persistence, and collective consensus. Our analysis reveals a system in dynamic balance in Moltbook: while global semantic averages stabilize rapidly, individual agents retain high diversity and persistent lexical turnover, defying homogenization. However, agents exhibit strong individual inertia and minimal adaptive response to interaction partners, preventing mutual influence and consensus. Consequently, influence remains transient with no persistent supernodes, and the society fails to develop stable collective influence anchors due to the absence of shared social memory. These findings demonstrate that scale and interaction density alone are insufficient to induce socialization, providing actionable design and analysis principles for upcoming next-generation AI agent societies.
There are no more articles
❌