Semantic Cooperative Games Enable Efficient Contribution Attribution in LLM-Based Multi-Agent Systems
A new framework called Semantic Cooperative Games (SCG) is introduced for attributing agent contributions in large language model (LLM)-based multi-agent systems. The proposed SLIC algorithm leverages a semantic hypergraph to capture intermediate states, enabling attribution without repeated model calls. On a medical benchmark, SLIC reduces computation cost by 93.3% while maintaining high consistency with Monte Carlo Shapley baselines. The method also reveals nuanced differences between semantic contribution and failure impact in complex workflows.
Why it matters: This work offers a significant advance in efficiently and interpretably attributing agent contributions in complex LLM-based multi-agent systems, which is important for debugging and improving such systems.
Full story at: arXiv AI/ML ↗