{"total":585,"rows":[{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501,"area":"agents"},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309,"area":null},{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142,"area":"agents"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2604.01687","title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","created":"2026-04-02","cited_by_count":128,"area":"agents"},{"id":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","created":"2026-06-08","cited_by_count":107,"area":"agents"},{"id":"2603.15401","title":"SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?","created":"2026-03-16","cited_by_count":82,"area":"agents"},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2604.04323","title":"How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings","created":"2026-04-06","cited_by_count":65,"area":"agents"},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64,"area":"agents"},{"id":"2603.25723","title":"Natural-Language Agent Harnesses","created":"2026-03-26","cited_by_count":61,"area":null},{"id":"2605.26494","title":"The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence","created":"2026-05-26","cited_by_count":61,"area":"agents"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2605.27922","title":"Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows","created":"2026-05-27","cited_by_count":57,"area":"agents"},{"id":"2607.07946","title":"DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks","created":"2026-07-08","cited_by_count":49,"area":"agents"},{"id":"2607.12227","title":"Rethinking the Evaluation of Harness Evolution for Agents","created":"2026-07-14","cited_by_count":48,"area":"lr"},{"id":"2604.24005","title":"TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents","created":"2026-04-27","cited_by_count":47,"area":"lr"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"area":null},{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2605.05726","title":"SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents","created":"2026-05-07","cited_by_count":39,"area":"agents"},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2605.05242","title":"Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction","created":"2026-05-03","cited_by_count":38,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2605.30621","title":"Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents","created":"2026-05-28","cited_by_count":34,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2606.05405","title":"Agents' Last Exam","created":"2026-06-03","cited_by_count":31,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"area":"agents"},{"id":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"area":"agents"},{"id":"2606.24597","title":"Qwen-AgentWorld: Language World Models for General Agents","created":"2026-06-23","cited_by_count":28,"area":"wm"},{"id":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2604.17308","title":"SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents","created":"2026-04-19","cited_by_count":25,"area":null},{"id":"2603.22386","title":"From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents","created":"2026-03-23","cited_by_count":24,"area":"agents"},{"id":"2602.10999","title":"CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","cited_by_count":22,"area":null},{"id":"2606.17573","title":"Cordon: Semantic Transactions for Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2605.20876","title":"Terminal-World: Scaling Terminal-Agent Environments via Agent Skills","created":"2026-05-20","cited_by_count":20,"area":"agents"},{"id":"2606.16458","title":"RHO: Your Coding Agent is Secretly a Roboticist","created":"2026-06-15","cited_by_count":20,"area":"agents"},{"id":"2605.09252","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","created":"2026-05-10","cited_by_count":19,"area":"lr"},{"id":"2605.24517","title":"ECHO: Terminal Agents Learn World Models for Free","created":"2026-05-23","cited_by_count":19,"area":"wm"},{"id":"2606.05922","title":"Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference","created":"2026-06-04","cited_by_count":19,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2604.18394","title":"OpenGame: Open Agentic Coding for Games","created":"2026-04-20","cited_by_count":18,"area":"agents"},{"id":"2605.18401","title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","created":"2026-05-18","cited_by_count":18,"area":"agents"},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18,"area":"agents"},{"id":"2607.25886","title":"RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement","created":"2026-07-28","cited_by_count":18,"area":"synth"},{"id":"2609.14858","title":"Dream-RSI: Recursive Self-Improvement through Evolving Worlds","created":"2026-09-14","cited_by_count":18,"area":null},{"id":"2604.23781","title":"ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents","created":"2026-04-26","cited_by_count":17,"area":"agents"},{"id":"2607.05804","title":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training","created":"2026-07-07","cited_by_count":17,"area":"distill"},{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"id":"2608.01918","title":"HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses","created":"2026-08-03","cited_by_count":17,"area":"agents"},{"id":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16,"area":"agents"},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2604.12290","title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","created":"2026-04-14","cited_by_count":16,"area":"agents"},{"id":"2606.30560","title":"TraceLab: Characterizing Coding Agent Workloads for LLM Serving","created":"2026-06-29","cited_by_count":16,"area":"agents"},{"id":"2607.14159","title":"MemoHarness: Agent Harnesses That Learn from Experience","created":"2026-07-14","cited_by_count":16,"area":"agents"},{"id":"2608.15071","title":"Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents","created":"2026-08-15","cited_by_count":16,"area":"agents"},{"id":"2608.25593","title":"JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution","created":"2026-08-26","cited_by_count":16,"area":"agents"},{"id":"2604.16529","title":"Scaling Test-Time Compute for Agentic Coding","created":"2026-04-16","cited_by_count":15,"area":"lr"},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2604.24955","title":"BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks","created":"2026-04-27","cited_by_count":15,"area":"agents"},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2608.23041","title":"AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces","created":"2026-08-24","cited_by_count":15,"area":"agents"},{"id":"2602.22480","title":"VeRO: A Harness for Agents to Optimize Agents","created":"2026-02-25","cited_by_count":14,"area":"agents"},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"area":"lr"},{"id":"2607.13683","title":"HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution","created":"2026-07-15","cited_by_count":14,"area":"agents"},{"id":"2602.11224","title":"Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation","created":"2026-02-11","cited_by_count":13,"area":"agents"},{"id":"2602.22953","title":"General Agent Evaluation","created":"2026-02-26","cited_by_count":13,"area":"agents"},{"id":"2604.28138","title":"Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes","created":"2026-04-30","cited_by_count":13,"area":"agents"},{"id":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"area":"agents"},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2607.13285","title":"Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable","created":"2026-07-14","cited_by_count":13,"area":"agents"},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2608.19880","title":"EnvHarness: Awakening Static Worlds for Agent Learning","created":"2026-08-20","cited_by_count":13,"area":"agents"},{"id":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2605.10913","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2605.25430","title":"CODESKILL: Learning Self-Evolving Skills for Coding Agents","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2606.06741","title":"OpenSkill: Open-World Self-Evolution for LLM Agents","created":"2026-06-04","cited_by_count":12,"area":"agents"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"}],"next_cursor":"100"}