{"total":15,"rows":[{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2608.19760","title":"Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay","created":"2026-08-20","cited_by_count":7,"area":"agents"},{"id":"2608.06909","title":"Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework","created":"2026-08-07","cited_by_count":4,"area":"agents"},{"id":"2608.29942","title":"Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2608.29228","title":"Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.06445","title":"Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.20625","title":"Chronicle: Cut-Point Replay for Regression Testing of LLM Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.32498","title":"DAAF: From Failure Localization to Editable System Assets in LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34177","title":"ReplayLens: Auditing Agents' Use of Outcomes","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34215","title":"Same Winners, Different Success Rates: Evaluating How LLM Agents Recover from Failures","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34649","title":"Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38661","title":"EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.00372","title":"When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.04375","title":"Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.09088","title":"RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}