{"total":24,"rows":[{"id":"2601.11044","title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","created":"2026-01-16","cited_by_count":28,"area":"agents"},{"id":"2512.21720","title":"An Information Theoretic Perspective on Agentic System Design","created":"2025-12-25","cited_by_count":8,"area":"agents"},{"id":"2602.16179","title":"EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments","created":"2026-02-18","cited_by_count":8,"area":"agents"},{"id":"2603.18096","title":"A Trace-Based Assurance Framework for Agentic AI Orchestration: Contracts, Testing, and Governance","created":"2026-03-18","cited_by_count":8,"area":"agents"},{"id":"2601.00481","title":"MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability","created":"2026-01-01","cited_by_count":7,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2601.09032","title":"The Hierarchy of Agentic Capabilities: Evaluating Frontier Models on Realistic RL Environments","created":"2026-01-13","cited_by_count":5,"area":"agents"},{"id":"2602.01415","title":"Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents","created":"2026-02-01","cited_by_count":3,"area":"agents"},{"id":"2606.09118","title":"ComplexConstraints and Beyond: Expert Rubrics for RLVR","created":"2026-06-08","cited_by_count":3,"area":"agents"},{"id":"2603.04241","title":"Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows","created":"2026-03-04","cited_by_count":2,"area":"agents"},{"id":"2604.00356","title":"Signals: Trajectory Sampling and Triage for Agentic Interactions","created":"2026-04-01","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":"2607.04034","title":"The \"I Don't Know\" Filter: Enhancing Agentic Reliability in Function Calling","created":"2026-07-04","cited_by_count":2,"area":"agents"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2607.11698","title":"Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2602.05302","title":"PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2604.02500","title":"I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime","created":"2026-04-02","cited_by_count":1,"area":"agents"},{"id":"2604.01647","title":"Exploring Robust Multi-Agent Workflows for Environmental Data Management","created":"2026-04-02","cited_by_count":0,"area":"agents"},{"id":"2604.17817","title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","created":"2026-04-20","cited_by_count":0,"area":"agents"},{"id":"2605.30539","title":"A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.13994","title":"Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH","created":"2026-06-12","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":"2610.14115","title":"The Silent Failures in Agentic Data Science","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.19367","title":"Beyond Corrected Actions: Training LLM Agents on Textual Critiques","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}