ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making

TL;DR

ComplLLM is a fine-tuning framework for large language models that enhances decision-making by discovering and leveraging complementary signals from multiple agents, improving decision quality and interpretability.

Contribution

It introduces a novel post-training fine-tuning method based on decision theory to identify and utilize complementary information in multi-agent decision pipelines.

Findings

Recovers known complementary signals in synthetic tasks

Produces plausible explanations of complementary signals

Enhances decision-making performance in real-world tasks

Abstract

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to the table to inform a final decision. We propose ComplLLM, a post-training framework based on decision theory that fine-tunes a decision-assistant LLM using complementary information as reward to output signals that complement existing agent decisions. We validate ComplLLM on synthetic and real-world tasks involving domain experts, demonstrating how the approach recovers known complementary information and produces plausible explanations of complementary signals to support downstream decision-makers.