{"total":19,"rows":[{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"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":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2408.13406","title":"Collaboration Dynamics and Reliability Challenges of Multi-Agent LLM Systems in Finite Element Analysis","created":"2024-08-23","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2605.07728","title":"SARC: A Governance-by-Architecture Framework for Agentic AI Systems","created":"2026-05-08","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":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2607.28196","title":"Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution","created":"2026-07-30","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":"2604.17989","title":"AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum","created":"2026-04-20","cited_by_count":0,"area":"agents"},{"id":"2607.18064","title":"Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.20527","title":"Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2608.05990","title":"OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2609.04217","title":"At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent","created":"2026-06-25","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":"2610.09377","title":"From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.18355","title":"ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}