{"total":15,"rows":[{"id":"2606.09863","title":"From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents","created":"2026-06-01","cited_by_count":15,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2603.29665","title":"Near-Miss: Latent Policy Failure Detection in Agentic Workflows","created":"2026-03-31","cited_by_count":4,"area":"agents"},{"id":"2603.12564","title":"Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents","created":"2026-03-13","cited_by_count":2,"area":"agents"},{"id":"2607.27275","title":"Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.06329","title":"Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.20314","title":"MidTool: Mid-training Data Synthesis for Agentic Tool Use","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.26911","title":"TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents","created":"2026-09-22","cited_by_count":1,"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":"2608.15286","title":"No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2609.25686","title":"How Strongly Should Task State Influence an LLM Agent?","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.29547","title":"When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.32255","title":"Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34132","title":"From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39989","title":"What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}