AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents Paper • 2607.18754 • Published 5 days ago • 24
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems Paper • 2512.06749 • Published Dec 7, 2025 • 28
SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs Paper • 2510.25092 • Published Oct 29, 2025 • 8
Where LLM Agents Fail and How They can Learn From Failures Paper • 2509.25370 • Published Sep 29, 2025 • 12