{"total":30,"rows":[{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2602.00933","title":"MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers","created":"2026-01-31","cited_by_count":53,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"id":"2601.11044","title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","created":"2026-01-16","cited_by_count":28,"area":"agents"},{"id":"2602.22897","title":"OmniGAIA: Towards Native Omni-Modal AI Agents","created":"2026-02-26","cited_by_count":22,"area":"agents"},{"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":"2602.07962","title":"LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth","created":"2026-02-08","cited_by_count":14,"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":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7,"area":"agents"},{"id":"2601.14914","title":"CodeDelegator: Mitigating Context Pollution via Role Separation in Code-as-Action Agents","created":"2026-01-21","cited_by_count":4,"area":"agents"},{"id":"2604.01532","title":"PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools","created":"2026-04-02","cited_by_count":4,"area":"agents"},{"id":"2602.15945","title":"From Tool Orchestration to Code Execution: A Study of MCP Design Choices","created":"2026-02-17","cited_by_count":3,"area":"agents"},{"id":"2608.19741","title":"One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2608.27260","title":"What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2609.29095","title":"Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents","created":"2026-09-24","cited_by_count":3,"area":"agents"},{"id":"2604.07551","title":"MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2605.17453","title":"Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2607.23722","title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios","created":"2026-07-26","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":"2609.05837","title":"AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories","created":"2026-09-05","cited_by_count":2,"area":"agents"},{"id":"2606.13994","title":"Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.11126","title":"ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.13987","title":"Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.23142","title":"CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.29892","title":"Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.31301","title":"Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.32776","title":"On the Behavioral Traits of LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34313","title":"ControlScope: Workflow Revision and Reliability in LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.14966","title":"SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.16867","title":"Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}