{"total":17,"rows":[{"id":"2606.16458","title":"RHO: Your Coding Agent is Secretly a Roboticist","created":"2026-06-15","cited_by_count":20,"area":"agents"},{"id":"2608.04828","title":"Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?","created":"2026-08-05","cited_by_count":10,"area":"agents"},{"id":"2608.06301","title":"HarnessOpt-Bench: Evaluating LLMs at Harness Optimization","created":"2026-08-06","cited_by_count":9,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2607.01213","title":"RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.25415","title":"A Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2607.02873","title":"Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.25408","title":"Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.23953","title":"The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.18844","title":"ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts","created":"2026-09-16","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":"2609.35501","title":"SRHarness: A Harness for Agentic Symbolic Regression","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.04433","title":"What Does a Harness Buy? Tokens, Mostly","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.04921","title":"Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.05778","title":"MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06069","title":"Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.08364","title":"Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}