Developing story · 2 episodes · 15 Sept to 24 Sept
AI Agent Insight and Collaboration Saga
The saga chronicles advances in AI agent failure attribution and multi-LLM collaboration. After the latest episode, the COMED framework now enhances multi-LLM inference through selective collaboration, building on earlier breakthroughs in failure attribution accuracy.
-
COMED improves multi-LLM inference with selective collaboration
Researchers introduced COMED, a post-anchor controller designed to optimize multi-LLM inference by selectively invoking peer models. The system addresses the limitations of current approaches, where…
1 source primary source -
Continual Search framework boosts AI agent failure attribution accuracy on large logs
The paper tackles the challenge of diagnosing failures in long‑horizon AI agents, where execution logs can span thousands of steps and human review is infeasible. Existing root‑cause attribution…
1 source primary source
Who and what