{"total":14,"rows":[{"id":"2605.30611","title":"Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs","created":"2026-05-28","cited_by_count":9,"area":null},{"id":"2604.22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2605.10870","title":"Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2605.12239","title":"Harness Engineering as Categorical Architecture","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.25045","title":"AION: Next-Generation Tasks and Practical Harness for Time Series","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2605.29682","title":"Scaling Laws for Agent Harnesses via Effective Feedback Compute","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.05050","title":"Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2605.18476","title":"AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2609.33123","title":"Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02920","title":"HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05382","title":"Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15714","title":"MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}