AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems

arXiv:2604.11978v1 Announce Type: new Abstract: Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that

arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment

arXiv:2603.25001v1 Announce Type: new Abstract: Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks and methods

<p>The blind spot in current AI guardrails</p> <p>Guardrail middleware for AI agents is maturing fast. LangChain ships native guardrails. NeMo Guardrails and Guardrails AI are

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers.

arXiv:2607.18754v1 Announce Type: new Abstract: LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing

arXiv:2607.29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This

arXiv:2605.01604v1 Announce Type: new Abstract: Existing evaluation frameworks for large language models -- including HELM, MT-Bench, AgentBench, and BIG-bench -- are designed for