Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
We propose SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief.
ProofPaper ↗
Key points
- LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents.
- In this work, we focus on parallel multi-agent reasoning systems, where several agents solve the same problem over multiple rounds and aggregate their outputs into a final answer.
- Despite their strong reasoning performance, uncertainty estimation for such systems remains underexplored: the reliability of a MAS depends not only on individual generations, but also on how agents interact and evolve across rounds.
- SAUCE aggregates round-level agreement and generation-uncertainty signals through a filtering-style update.
Sources (1)
- [1]Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning SystemsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:58 PM
We propose SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief.
LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents.
Extractive summary: sentences quoted from the sources.