{"total":92,"rows":[{"id":"2605.27922","title":"Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows","created":"2026-05-27","cited_by_count":57,"area":"agents"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2602.17753","title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","created":"2026-02-19","cited_by_count":30,"area":"agents"},{"id":"2604.11978","title":"The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break","created":"2026-04-13","cited_by_count":25,"area":"agents"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2602.22953","title":"General Agent Evaluation","created":"2026-02-26","cited_by_count":13,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2603.23749","title":"Efficient Benchmarking of AI Agents","created":"2026-03-24","cited_by_count":10,"area":"agents"},{"id":"2605.08545","title":"Log analysis is necessary for credible evaluation of AI agents","created":"2026-05-08","cited_by_count":10,"area":null},{"id":"2605.20530","title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","created":"2026-05-19","cited_by_count":10,"area":"agents"},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2606.11447","title":"AI Coding Agents Can Reproduce Social Science Findings","created":"2026-06-09","cited_by_count":6,"area":"agents"},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2606.26158","title":"Life After Benchmark Saturation: A Case Study of CORE-Bench","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2608.13417","title":"Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development","created":"2026-08-13","cited_by_count":4,"area":null},{"id":"2608.18066","title":"On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification","created":"2026-08-18","cited_by_count":4,"area":"synth"},{"id":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2607.05775","title":"Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"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":"2609.26760","title":"Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents","created":"2026-09-22","cited_by_count":3,"area":"agents"},{"id":"2609.29095","title":"Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents","created":"2026-09-24","cited_by_count":3,"area":"agents"},{"id":"2511.12306","title":"UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI","created":"2025-11-15","cited_by_count":2,"area":"agents"},{"id":"2605.19149","title":"Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.22564","title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2606.13608","title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2606.17541","title":"Offline Preference-Based Trajectory Evaluation","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.20629","title":"Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2607.02931","title":"VERITAS: Towards a General-Purpose Replication Tool for Scientific Research","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.04075","title":"PatchBench: Evaluating AI Agents for Vulnerability Patching","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2602.06841","title":"From Features to Actions: Explainability in Traditional and Agentic AI Systems","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2602.18460","title":"The Doctor Will (Still) See You Now: On the Structural Limits of Agentic AI in Healthcare","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2604.23897","title":"MarketBench: Evaluating AI Agents as Market Participants","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.18671","title":"HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.02444","title":"ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.20370","title":"Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.38345","title":"OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime","created":"2026-09-29","cited_by_count":1,"area":null},{"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":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.08872","title":"How does Chain of Thought decompose complex tasks?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.06177","title":"BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2606.01581","title":"Agent System Operations: Categorization, Challenges, and Future Directions","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.10711","title":"The Agentic Web Requires New Normative Infrastructure","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.20610","title":"Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.00297","title":"EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.02703","title":"LLMoxie: Exploring Agentic AI for Scientific Software Development","created":"2026-07-02","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":"2607.22689","title":"Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"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":"2608.04336","title":"COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05784","title":"Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.08709","title":"AI Evaluation Should Measure Verification Cost, Not Correctness Alone","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.28590","title":"DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2609.01466","title":"Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.03153","title":"VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement","created":"2026-09-02","cited_by_count":0,"area":"wm"},{"id":"2609.11018","title":"Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.12404","title":"VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.14500","title":"When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems","created":"2026-09-13","cited_by_count":0,"area":null},{"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":"2609.21325","title":"LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.21841","title":"EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.26048","title":"FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents","created":"2026-09-22","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":"2609.32213","title":"HM-ROUTER: Joint Model and Harness Routing for Agentic Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32776","title":"On the Behavioral Traits of LLM Agents","created":"2026-09-26","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":"2609.33980","title":"DynGraphAgentBench: A Benchmark for Agentic Lifecycle Control in Dynamic Graph Anomaly Detection","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.38137","title":"LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38372","title":"Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer","created":"2026-09-29","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":"2610.00651","title":"Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00791","title":"Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01110","title":"How Much Can Language Models Gain from Test-Time Computation?","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04824","title":"Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.05830","title":"Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.14539","title":"FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18789","title":"Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Response","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18813","title":"Self-Evolving Agent Harness","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}