| 2026-11-13 | 2611.17834 | PaperCritic: Training AI Reviewers to Assess the Soundness of Papers | Hyun Ryu et al. | arXiv | 32 | |
| 2026-11-13 | 2611.16728 | EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming | Yaru Niu et al. | arXiv | 1 | |
| 2026-11-09 | 2611.01362 | "PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper Retrieval | Jingjie Ning et al. | arXiv | 6 | |
| 2026-11-09 | W7147594723 | TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space | Zhixuan Liu et al. | ACM Transactions on Graphics | | |
| 2026-10-31 | 2611.00883 | Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand | George Ling et al. | arXiv | 49 | |
| 2026-10-30 | W7224843773 | BitterBuster: A virtual world for understanding naturalistic patch foraging | John P. Kasarda et al. | PLoS ONE | | |
| 2026-10-29 | 2610.40564 | Training Foundation Models with a Single Algorithm | Yuda Song et al. | arXiv | 8 | |
| 2026-10-28 | 2610.34714 | SearchHorizonBench: A Benchmark for Search Value in AI Agents | Jingjie Ning et al. | arXiv | 11 | |
| 2026-10-28 | 2610.29003 | T-DIG: Text-Conditioned Diversity for Image Generation | Simran Khanuja et al. | arXiv | 8 | |
| 2026-10-28 | 2610.33245 | AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science | Atharva Naik et al. | arXiv | 3 | |
| 2026-10-27 | 2610.34634 | AgentProofBench: Benchmarking Reusable Verifiers for Web Agents | Jingjie Ning et al. | arXiv | 12 | |
| 2026-10-24 | 2610.33512 | Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL | Hyun Ryu et al. | arXiv | 47 | |
| 2026-10-21 | 2610.23010 | What Makes a Good Symbol for Hybrid Discrete-Continuous Planning? | Yiyuan Pan et al. | arXiv | 2 | |
| 2026-10-19 | 2610.19159 | Into the Unknown: Benchmarking AI agents on open scientific research problems | Seungone Kim et al. | arXiv | 62 | |
| 2026-10-14 | 2610.16811 | X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning | Yi Wang et al. | arXiv | 34 | |
| 2026-10-14 | 2610.18579 | Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops | Yubo Li et al. | arXiv | 9 | |
| 2026-10-08 | 2610.05034 | Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads | Jingjie Ning et al. | arXiv | 10 | |
| 2026-10-07 | 2610.01892 | Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents | Feiyu Gavin Zhu et al. | arXiv | 32 | |
| 2026-10-02 | 2610.00314 | Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts | Jingjie Ning et al. | arXiv | 11 | |
| 2026-10-02 | 2610.00313 | Rules to Tools: Executable Checks for LLM Agents in Scientific Computing | Jingjie Ning et al. | arXiv | 5 | |
| 2026-10-01 | 2609.32720 | BiasReducer: Adaptive Bias Mitigation for Reward Models | Shuang Liu et al. | arXiv | 25 | |
| 2026-10-01 | 2609.32600 | CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering | Prince Zizhuang Wang et al. | arXiv | 15 | |
| 2026-09-29 | 2609.34313 | ControlScope: Workflow Revision and Reliability in LLM Agents | Jingjie Ning et al. | arXiv | 3 | |
| 2026-09-28 | 2609.30222 | TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations | Ayush Jain et al. | arXiv | 14 | |
| 2026-09-25 | 2609.28654 | Training Object Permanence in World Models | Haotian Zhang et al. | arXiv | 112 | |
| 2026-09-24 | 2609.27490 | WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents | Jingjie Ning et al. | arXiv | 15 | |
| 2026-09-23 | 2609.26550 | JEV-as-a-Judge: Accept When Confident, Escalate When Unsure | Yubo Li et al. | arXiv | 41 | |
| 2026-09-16 | 2609.16204 | Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration | Aashiq Muhamed et al. | arXiv | 4 | |
| 2026-09-14 | 2609.11115 | Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation | Koutian Wu et al. | arXiv | 153 | |
| 2026-09-10 | 2609.09219 | Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents | Jingjie Ning et al. | arXiv | 13 | |
| 2026-09-09 | 2609.08345 | CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs | Nhat-Tan Bui et al. | arXiv | 9 | |
| 2026-09-09 | 2609.06966 | MOLE: Detecting Insider Threats in AI Agents | Aashiq Muhamed et al. | arXiv | 4 | |
| 2026-08-25 | 2608.22856 | Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA | Jingjie Ning et al. | arXiv | 4 | |
| 2026-08-19 | 2608.16977 | The Problem Is the Problem: Towards Scalable Mathematical Discovery | Zeyu Zheng et al. | arXiv | 7 | |
| 2026-08-17 | 2608.13760 | Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models | Jean de Dieu Nyandwi et al. | arXiv | 4 | |
| 2026-08-11 | 2608.03499 | WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks | Prince Zizhuang Wang et al. | arXiv | 7 | |
| 2026-07-27 | 2607.18142 | O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning | Mei Yuan et al. | arXiv | 2 | |
| 2026-06-30 | 2606.00097 | RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets | Peter Pak et al. | arXiv | 6 | |
| 2026-06-23 | 2606.23608 | Causal Discovery in the Era of Agents | Yujia Zheng et al. | arXiv | 8 | |
| 2026-06-18 | 2606.16748 | MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents | Lawrence Keunho Jang et al. | arXiv | 6 | |
| 2026-06-18 | 2606.09764 | iOSWorld: A Benchmark for Personally Intelligent Phone Agents | Lawrence Keunho Jang et al. | arXiv | 4 | |
| 2026-06-09 | 2606.08960 | Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops | Ziqian Zhong et al. | arXiv | 2 | |
| 2026-06-02 | 2606.02404 | K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts | Nahyun Lee et al. | arXiv | 56 | |
| 2026-06-02 | 2605.29084 | Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG | Yubo Li et al. | arXiv | 1 | |
| 2026-06-02 | 2605.29087 | The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure | Yubo Li et al. | arXiv | 1 | |
| 2026-05-29 | 2605.24785 | PANDO: Efficient Multimodal AI Agents via Online Skill Distillation | Yubo Li et al. | arXiv | 5 | |
| 2026-05-29 | 2605.25220 | Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation | Aviral Chharia et al. | arXiv | 4 | |
| 2026-05-29 | 2605.24786 | CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM | Yubo Li et al. | arXiv | 3 | |
| 2026-05-28 | 2605.26457 | Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization | Anmol Agarwal et al. | arXiv | 4 | |
| 2026-05-25 | 2605.17766 | LatentUMM: Dual Latent Alignment for Unified Multimodal Models | Yinyi Luo et al. | arXiv | 7 | |
| 2026-05-21 | 2605.20668 | On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists | Seungone Kim et al. | arXiv | 13 | |
| 2026-05-20 | 2605.19516 | Base Models Look Human To AI Detectors | Yixuan Even Xu et al. | arXiv | 1 | |
| 2026-05-19 | 2605.15565 | AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs | Haizhong Zheng et al. | arXiv | 15 | |
| 2026-05-19 | 2605.16865 | MixSD: Mixed Contextual Self-Distillation for Knowledge Injection | Jiarui Liu et al. | arXiv | 8 | |
| 2026-05-14 | 2605.12733 | From Generalist to Specialist Representation | Yujia Zheng et al. | arXiv | 1 | |
| 2026-05-08 | 2605.05724 | Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes | Jingjie Ning et al. | arXiv | 15 | |