Tag
This paper formalizes agent coalition formation and inter-agent communication as a cooperative game, proposing marginal-value activation rules and Shapley-based online routing to reduce token costs and improve efficiency in multi-agent LLM systems, with theoretical guarantees and synthetic simulation results.
This paper introduces SkillSV, a structure-aware Shapley-style framework for valuing the internal units of agent skills, accounting for dependencies and hierarchy. It demonstrates improved faithfulness, actionability, and explanation quality on agentic benchmarks.
Introduces a scalable, inference-only data valuation pipeline that approximates Shapley values to audit LLM alignment datasets, reducing manual audit search space by 99.1% and uncovering hidden label failures in HelpSteer2 and HH-RLHF.
Proposes Semantic Cooperative Games (SCG) and Semantic Shapley Value (SSV) for contribution attribution in LLM-based multi-agent systems, introducing a single-trajectory algorithm SLIC that reduces computation cost by 93.3% while remaining consistent with Monte Carlo Shapley baselines.
This paper introduces a class of nonlinear axiomatic attribution methods for cooperative games to overcome the limitations of the linear Shapley value, which has an excessively large null space. Experimental results demonstrate the potential effectiveness of these methods in terms of inclusion AUC metric compared to Shapley value variants.
Proposes DAG-SHAP, a novel feature attribution method based on edge intervention for directed acyclic graphs, addressing limitations of existing Shapley value methods in capturing feature interactions and causal relationships.
SHAPE proposes a coalition-aware expert pruning framework for sparse MoE LLMs that uses Shapley-style attribution over routing traces to identify essential experts, achieving competitive accuracy under 20-40% pruning and reducing GPU memory footprint.
This paper proposes Temporal-Decay Shapley (TDS), a data valuation framework for time-series data that incorporates temporal decay and multi-scale fusion to address the time-varying nature of sample values, outperforming traditional methods in noise detection and data selection.