{"total":16,"rows":[{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"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":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"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":"2511.21444","title":"EWE: An Agentic Framework for Extreme Weather Analysis","created":"2025-11-26","cited_by_count":4,"area":"agents"},{"id":"2606.05920","title":"Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement","created":"2026-06-04","cited_by_count":4,"area":"agents"},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2604.26020","title":"Training Computer Use Agents to Assess the Usability of Graphical User Interfaces","created":"2026-04-28","cited_by_count":2,"area":"agents"},{"id":"2604.25914","title":"DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios","created":"2026-04-28","cited_by_count":1,"area":"agents"},{"id":"2609.33439","title":"Raven: The Harness of Harnesses for Composable Agentic Intelligence","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2609.26204","title":"WatchPoint: Executable User Feedback for Real-World Agentic Web Development","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2610.02617","title":"WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.06910","title":"GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.17895","title":"Interaction-as-a-Judge","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}