{"total":53,"rows":[{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2508.12685","title":"ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction","created":"2025-08-18","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":"2603.29139","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","created":"2026-03-31","cited_by_count":10,"area":"agents"},{"id":"2605.07161","title":"SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2604.05229","title":"From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI","created":"2026-04-06","cited_by_count":7,"area":"agents"},{"id":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2605.20251","title":"ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2605.13139","title":"SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle","created":"2026-05-13","cited_by_count":5,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2605.12105","title":"Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts","created":"2026-05-12","cited_by_count":3,"area":"agents"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","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":"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":"2601.09883","title":"Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2604.19818","title":"Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AI","created":"2026-04-18","cited_by_count":2,"area":"agents"},{"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":"2608.08775","title":"OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2609.00949","title":"Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.06815","title":"Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents","created":"2026-09-06","cited_by_count":2,"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":"2601.15290","title":"Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios","created":"2025-11-30","cited_by_count":1,"area":"agents"},{"id":"2603.15976","title":"An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.23263","title":"SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents","created":"2026-07-25","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":"2608.00794","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","created":"2026-08-01","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":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.08468","title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.26195","title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","created":"2026-05-25","cited_by_count":0,"area":"agents"},{"id":"2605.28556","title":"A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","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":"2609.26826","title":"What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus","created":"2026-09-20","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":"2609.33812","title":"Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35143","title":"Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut","created":"2026-09-28","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":"2610.03585","title":"Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.11678","title":"TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation","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"}],"next_cursor":null}