Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training Paper • 2609.40111 • Published Sep 30 • 32
DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter Paper • 2610.17666 • Published Oct 13 • 26
JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs Paper • 2610.21412 • Published Oct 15 • 24
CUADebug: Diagnosing and Repairing Computer-Use Agent Failures Paper • 2608.02643 • Published Sep 6 • 6
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents Paper • 2607.18754 • Published Jul 21 • 25 • 4
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents Paper • 2607.18754 • Published Jul 21 • 25
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 63
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published Mar 17 • 103
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper • 2509.18154 • Published Sep 16, 2025 • 65
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal Paper • 2601.18081 • Published Jan 26 • 7
AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning Paper • 2511.19304 • Published Nov 24, 2025 • 90
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems? Paper • 2509.03312 • Published Sep 3, 2025 • 6
Multi-Agent Evolve: LLM Self-Improve through Co-evolution Paper • 2510.23595 • Published Oct 27, 2025 • 14