Papers

Filtered to debugging frameworks · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

21 upvotes · 21 JUL 2026 · Kunlun Zhu, Xuyan Ye, Zhiguang Han et al.

This paper introduces AgentDebugX, an open-source toolkit that helps debug and recover from failures in large language model (LLM) agents, making it easier to identify and fix errors. Practitioners can benefit from AgentDebugX as it provides a framework for detecting, attributing, and recovering from errors, which can improve the accuracy and reliability of LLM agents.

LLMdebugging frameworksfailure observabilityattributionrecoveryagent-based systems