{"total":36,"rows":[{"id":"2609.01437","title":"HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?","created":"2026-09-01","cited_by_count":13,"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":"2608.08466","title":"Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses","created":"2026-08-09","cited_by_count":7,"area":"agents"},{"id":"2609.24974","title":"Harness-Zero: Harness Distillation via Agent-as-Harness","created":"2026-09-21","cited_by_count":5,"area":"agents"},{"id":"2608.08311","title":"Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution","created":"2026-08-08","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":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"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":"2608.08793","title":"Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents","created":"2026-08-09","cited_by_count":1,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.17433","title":"Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2609.11028","title":"BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2609.19607","title":"DeltaSelect: Affordable A/B Testing for Coding Agents","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.36777","title":"Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.00917","title":"Finding the Right Fit: Model-Harness Interactions across Agent Tasks","created":"2026-10-01","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":"2609.10824","title":"Studying Without a Syllabus: Task-Agnostic Environment Preprocessing","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.11987","title":"Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.26693","title":"Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.32213","title":"HM-ROUTER: Joint Model and Harness Routing for Agentic Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34274","title":"BIABench: Evaluating AI agents on real-world bioimage analysis tasks","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36630","title":"Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.36887","title":"WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39551","title":"RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00372","title":"When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents","created":"2026-09-30","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":"2610.05778","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"},{"id":"2610.11552","title":"Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12183","title":"A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.14146","title":"Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.18090","title":"AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20344","title":"Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}