Training Advisors for LLM Agents from Task Outcomes
Caddie trains an outcome-based critic that lifts LLM agent success, including a 25-point gain for Qwen3-4B.
Stories per day · 30 days
2 RSS
6 stories, newest first · one card per story
Stories tagged #musique
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
An agentic RAG budget study finds broader question coverage reduces evaluation error more than extra reads or trajectories.
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
A rank-8 LoRA lets frozen transformers follow much longer in-context reference chains.
BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation
BaRe-Mem tracks advisor reliability so multi-agent systems resist misleading consultations better than debate or voting.
Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
Mara Chain refines rejected AI candidates, beating GEPA on AppWorld with 65.5% fewer rollouts.
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
RegimeAbstain uses structural retrieval features to abstain on predictable multi-hop failures, cutting confident wrong answers.