ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
This work addresses decision-making in multi-agent systems for domain experts, but it is incremental as it builds on existing fine-tuning and decision theory methods.
The paper tackles the problem of enhancing multi-agent decision pipelines by fine-tuning LLMs to generate complementary signals, and demonstrates the approach on synthetic and real-world tasks with domain experts, showing it recovers known complementary information and provides plausible explanations.
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.