{"total":32,"rows":[{"id":"2602.07150","title":"On Randomness in Agentic Evals","created":"2026-02-06","cited_by_count":17,"area":"agents"},{"id":"2506.00066","title":"Literature Review Of Multi-Agent Debate For Problem-Solving","created":"2025-05-29","cited_by_count":15,"area":"agents"},{"id":"2608.07545","title":"DarwinX: Evolving Agent Harnesses Through Natural Selection","created":"2026-07-31","cited_by_count":13,"area":"agents"},{"id":"2512.06710","title":"Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation","created":"2025-12-07","cited_by_count":11,"area":"agents"},{"id":"2601.20617","title":"Agent Benchmarks Fail Public Sector Requirements","created":"2026-01-28","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2608.30730","title":"E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation","created":"2026-08-31","cited_by_count":2,"area":"agents"},{"id":"2510.21524","title":"EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law","created":"2025-10-24","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","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":"2610.00609","title":"Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2606.19380","title":"ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2607.02975","title":"Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.06411","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.22331","title":"Noise Floor Audit for Agent Benchmarks","created":"2026-08-23","cited_by_count":0,"area":"agents"},{"id":"2609.14239","title":"CoArena: Evaluating Computer-Use and Multi-Agent Systems in Real Time","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.25173","title":"Attack Success Rate Is Not a Number: On Measurement Validity in Agentic AI Security Evaluation","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.26261","title":"Coding Agents are Strong Prompt Optimizers","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30725","title":"Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.33717","title":"Self-Designed Evaluators and Warm Memory for Long-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33812","title":"Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02563","title":"OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine","created":"2026-10-01","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":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11655","title":"Harness Evolution Hits a Ceiling: When Weight Training Should Begin","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.14216","title":"Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.18354","title":"Choosing LLMs for Strategic Agent Interactions","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}