{"total":24,"rows":[{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158,"area":"agents"},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52,"area":"agents"},{"id":"2604.00594","title":"Agent psychometrics: Task-level performance prediction in agentic coding benchmarks","created":"2026-04-01","cited_by_count":11,"area":"agents"},{"id":"2603.23749","title":"Efficient Benchmarking of AI Agents","created":"2026-03-24","cited_by_count":10,"area":"agents"},{"id":"2603.08835","title":"MASEval: Extending Multi-Agent Evaluation from Models to Systems","created":"2026-03-09","cited_by_count":6,"area":"agents"},{"id":"2607.02032","title":"PACE: A Proxy for Agentic Capability Evaluation","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2609.19526","title":"Self Improvement via Fast Tree-search","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"id":"2609.02783","title":"EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2606.17541","title":"Offline Preference-Based Trajectory Evaluation","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2607.18063","title":"Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"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":"2609.19607","title":"DeltaSelect: Affordable A/B Testing for Coding Agents","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.33763","title":"SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities","created":"2026-09-27","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":"2608.01004","title":"Who Belongs in the Eval Set? A Capability-Taxonomy-Driven Pipeline for Curating Regression Eval Sets in Agent-Extensibility Platforms","created":"2026-08-02","cited_by_count":0,"area":"agents"},{"id":"2609.01603","title":"Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.17394","title":"Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.18909","title":"Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.21267","title":"Efficient Benchmarking in Production: A Study of an Evolving LLM Agent","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.24928","title":"Trajectory-Aware Benchmark Subset Selection for Cost-Efficient Software Engineering Agent Regression Testing","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.40284","title":"cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents","created":"2026-09-30","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"}],"next_cursor":null}