{"total":141,"rows":[{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587,"area":"agents"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"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":"2603.22455","title":"SkillRouter: Skill Routing for LLM Agents at Scale","created":"2026-03-23","cited_by_count":61,"area":"agents"},{"id":"2602.14234","title":"REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents","created":"2026-02-15","cited_by_count":49,"area":"agents"},{"id":"2603.15594","title":"OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data","created":"2026-03-16","cited_by_count":39,"area":"agents"},{"id":"2603.17187","title":"MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild","created":"2026-03-17","cited_by_count":37,"area":"agents"},{"id":"2604.06126","title":"Gym-Anything: Turn any Software into an Agent Environment","created":"2026-04-07","cited_by_count":27,"area":"agents"},{"id":"2604.11790","title":"ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection","created":"2026-04-13","cited_by_count":27,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","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":"2606.30616","title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","created":"2026-06-29","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":"2606.07591","title":"ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research","created":"2026-05-28","cited_by_count":17,"area":"agents"},{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"id":"2603.23231","title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2604.20801","title":"Synthesizing Multi-Agent Harnesses for Vulnerability Discovery","created":"2026-04-22","cited_by_count":13,"area":"agents"},{"id":"2603.04257","title":"Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory","created":"2026-03-04","cited_by_count":12,"area":"agents"},{"id":"2604.22840","title":"AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards","created":"2026-04-21","cited_by_count":11,"area":"agents"},{"id":"2605.12481","title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","created":"2026-05-12","cited_by_count":11,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2605.24218","title":"QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks","created":"2026-05-22","cited_by_count":11,"area":"agents"},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11,"area":"agents"},{"id":"2606.29955","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","created":"2026-06-29","cited_by_count":11,"area":"agents"},{"id":"2607.05202","title":"EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer","created":"2026-07-06","cited_by_count":11,"area":"agents"},{"id":"2606.22902","title":"Agent-as-a-Router: Agentic Model Routing for Coding Tasks","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2602.04634","title":"WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning","created":"2026-02-04","cited_by_count":9,"area":"agents"},{"id":"2603.27490","title":"AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents","created":"2026-03-29","cited_by_count":9,"area":"agents"},{"id":"2605.00803","title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","created":"2026-05-01","cited_by_count":9,"area":"agents"},{"id":"2603.27703","title":"KAT-Coder-V2 Technical Report","created":"2026-03-29","cited_by_count":8,"area":"agents"},{"id":"2604.14709","title":"HWE-Bench: Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks","created":"2026-04-16","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2603.08013","title":"PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents","created":"2026-03-09","cited_by_count":7,"area":"agents"},{"id":"2603.15309","title":"CCTU: A Benchmark for Tool Use under Complex Constraints","created":"2026-03-16","cited_by_count":7,"area":"agents"},{"id":"2605.17283","title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","created":"2026-05-17","cited_by_count":7,"area":"agents"},{"id":"2606.25819","title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2607.11185","title":"SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL","created":"2026-07-13","cited_by_count":7,"area":"agents"},{"id":"2608.01837","title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning","created":"2026-08-03","cited_by_count":7,"area":"agents"},{"id":"2603.22341","title":"T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search","created":"2026-03-21","cited_by_count":6,"area":"agents"},{"id":"2605.05007","title":"Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation","created":"2026-05-06","cited_by_count":6,"area":"agents"},{"id":"2605.14678","title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.16217","title":"Argus: Evidence Assembly for Scalable Deep Research Agents","created":"2026-05-15","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2609.20804","title":"An Empirical Study of Harness Design for Coding Agents","created":"2026-09-17","cited_by_count":6,"area":"agents"},{"id":"2602.07359","title":"W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents","created":"2026-02-07","cited_by_count":5,"area":"agents"},{"id":"2603.27742","title":"TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration","created":"2026-03-29","cited_by_count":5,"area":"agents"},{"id":"2604.19859","title":"DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data","created":"2026-04-21","cited_by_count":5,"area":"agents"},{"id":"2605.02801","title":"Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces","created":"2026-05-04","cited_by_count":5,"area":"agents"},{"id":"2605.07510","title":"InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search","created":"2026-05-08","cited_by_count":5,"area":"agents"},{"id":"2605.12070","title":"Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction","created":"2026-05-12","cited_by_count":5,"area":"agents"},{"id":"2606.10651","title":"Kwai Keye-VL-2.0 Technical Report","created":"2026-06-09","cited_by_count":5,"area":"agents"},{"id":"2606.12195","title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","created":"2026-06-10","cited_by_count":5,"area":"agents"},{"id":"2606.15367","title":"S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents","created":"2026-06-13","cited_by_count":5,"area":"agents"},{"id":"2606.30251","title":"TACO: Tool-Augmented Credit Optimization for Agentic Tool Use","created":"2026-06-29","cited_by_count":5,"area":"agents"},{"id":"2608.07645","title":"Mendel G\\\"odel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution","created":"2026-08-07","cited_by_count":5,"area":"agents"},{"id":"2608.16721","title":"GenRouter: Unified Workflow Routing for Agentic Image Generation","created":"2026-08-17","cited_by_count":5,"area":"agents"},{"id":"2603.12155","title":"GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2605.18548","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2605.29790","title":"Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2607.24112","title":"Scaling GUI Agents with Visual State Transitions","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2608.12323","title":"Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2603.29632","title":"An Empirical Study of Multi-Agent Collaboration for Automated Research","created":"2026-03-31","cited_by_count":3,"area":"agents"},{"id":"2605.06110","title":"On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.24486","title":"AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2605.26457","title":"Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization","created":"2026-05-26","cited_by_count":3,"area":"agents"},{"id":"2606.02470","title":"MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.08992","title":"SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning","created":"2026-06-08","cited_by_count":3,"area":"agents"},{"id":"2607.15193","title":"Plover: Steering GUI Agents through Plan-Centric Interaction","created":"2026-07-16","cited_by_count":3,"area":"agents"},{"id":"2608.16246","title":"CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"area":"agents"},{"id":"2602.03784","title":"Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2603.06065","title":"ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2604.02665","title":"AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2604.06452","title":"Learning to Interrupt in Language-based Multi-agent Communication","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2604.14609","title":"El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2604.25083","title":"Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization","created":"2026-04-28","cited_by_count":2,"area":"agents"},{"id":"2605.10365","title":"Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.28003","title":"ResearchMath-14K: Scaling Research-Level Mathematics via Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.13707","title":"Orchestra-o1: Omnimodal Agent Orchestration","created":"2026-06-10","cited_by_count":2,"area":"agents"},{"id":"2606.17321","title":"ProCUA-SFT Technical Report","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2607.00502","title":"A Task-State Representation for Long-Horizon Mobile GUI Agents","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.09217","title":"OpenProver: Agentic and Interactive Theorem Proving with Lean 4","created":"2026-07-10","cited_by_count":2,"area":"agents"},{"id":"2607.27155","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.04804","title":"Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.08160","title":"Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives","created":"2026-08-08","cited_by_count":2,"area":"agents"},{"id":"2608.17597","title":"HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2608.18389","title":"A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2609.05374","title":"CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2609.12818","title":"Online Video Agent Harness for Long Video Understanding","created":"2026-09-11","cited_by_count":2,"area":"agents"},{"id":"2603.19347","title":"Exploring the Agentic Frontier of Verilog Code Generation","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2604.07831","title":"Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2604.14256","title":"Evaluation of Agents under Simulated AI Marketplace Dynamics","created":"2026-04-15","cited_by_count":1,"area":"agents"},{"id":"2604.18356","title":"ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship","created":"2026-04-20","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}