aiqbench analysis
This research introduces Semantic Cooperative Games (SCG), a novel framework that addresses the high computational cost of attribution in LLM-based multi-agent systems by modeling language flows as semantic hypergraphs. By utilizing a single-trajectory algorithm called SLIC, the method eliminates the need for repeated model calls or rerunning agent subsets while maintaining consistency with classical Shapley value baselines on standard benchmarks. The approach offers an interpretable, counterfactual-free solution that significantly reduces computation costs without sacrificing accuracy in complex workflows involving ordered dependencies and intermediate semantic states.
Semantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems
arXiv:2607.18255v1 Announce Type: new Abstract: Contribution attribution has become a central problem in LLM-based multi-agent systems, where final outputs are produced through multiple agents, message exchanges, and ordered workflow dependencies. Existing attribution methods often rely on counterfactual valuation, such as removing agents or comparing score changes across altered agent subsets. In language-mediated workflows, these methods require repeated model calls, introduce high variance, and do not explicitly capture the intermediate semantic states through which agents produce, preserve, and transform task-relevant information. We propose Semantic Cooperative Games (SCG), a framework that represents a realized language flow as a semantic generation hypergraph and induces an agent-level semantic value function on this structure. We define the Semantic Shapley Value (SSV) to allocate contribution over semantic support logic, and introduce SLIC, a single-trajectory algorithm that constructs the semantic hypergraph, recovers minimal semantic supports, applies Boolean absorption, and computes SSV without rerunning agent subsets. We prove that SSV reduces to the classical Shapley value under standard set-based, fully observable, and no-order-dependence conditions. On a medical benchmark satisfying these conditions, SLIC reduces computation cost by 93.3% while remaining highly consistent with a Monte Carlo Shapley baseline. In more general multi-role workflows, SSV aligns with perturbation-induced score-drop profiles and exposes cases where semantic contribution and failure impact diverge. Overall, SLIC provides a fast, counterfactual-free, and interpretable attribution method for complex LLM-based multi-agent systems.
Abstract:Contribution attribution has become a central problem in LLM-based multi-agent systems, where final outputs are produced through multiple agents, message exchanges, and ordered workflow dependencies. Existing attribution methods often rely on counterfactual valuation, such as removing agents or comparing score changes across altered agent subsets. In language-mediated workflows, these methods require repeated model calls, introduce high variance, and do not explicitly capture the intermediate semantic states through which agents produce, preserve, and transform task-relevant information. We propose Semantic Cooperative Games (SCG), a framework that represents a realized language flow as a semantic generation hypergraph and induces an agent-level semantic value function on this structure. We define the Semantic Shapley Value (SSV) to allocate contribution over semantic support logic, and introduce SLIC, a single-trajectory algorithm that constructs the semantic hypergraph, recovers minimal semantic supports, applies Boolean absorption, and computes SSV without rerunning agent subsets. We prove that SSV reduces to the classical Shapley value under standard set-based, fully observable, and no-order-dependence conditions. On a medical benchmark satisfying these conditions, SLIC reduces computation cost by 93.3% while remaining highly consistent with a Monte Carlo Shapley baseline. In more general multi-role workflows, SSV aligns with perturbation-induced score-drop profiles and exposes cases where semantic contribution and failure impact diverge. Overall, SLIC provides a fast, counterfactual-free, and interpretable attribution method for complex LLM-based multi-agent systems.
Artificial Intelligence (cs.AI)
arXiv:2607.18255 [cs.AI]
(or arXiv:2607.18255v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.18255 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 312 words
Related coverage
Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies
arXiv · Sep 23, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
arXiv · Jul 23, 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026