{"total":25,"rows":[{"id":"2603.10165","title":"OpenClaw-RL: Train Any Agent Simply by Talking","created":"2026-03-10","cited_by_count":90,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2605.15040","title":"Orchard: An Open-Source Agentic Modeling Framework","created":"2026-05-14","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":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2607.12385","title":"PM-Bench: Evaluating Prospective Memory in LLM Agents","created":"2026-07-14","cited_by_count":7,"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":"2603.25226","title":"WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing","created":"2026-03-26","cited_by_count":4,"area":"agents"},{"id":"2605.19932","title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","created":"2026-05-19","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":"2609.08183","title":"NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness","created":"2026-09-08","cited_by_count":4,"area":"agents"},{"id":"2603.17973","title":"TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis","created":"2026-03-18","cited_by_count":3,"area":"agents"},{"id":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2605.03195","title":"Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2605.27531","title":"Agentic Separation Logic Specification Synthesis","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.28965","title":"Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2607.00440","title":"Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward Tracking","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2609.33243","title":"CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.02206","title":"KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.11593","title":"Runnable Commit Untangling for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13479","title":"A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}