Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

Computer Science > Artificial Intelligence [Submitted on 24 Jul 2026] Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems Mojtaba Eslami Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance or allow full broadcast. Both can be inefficient because token cost, latency, redundancy, and error propagation increase with the number of active agents and communication links. We model agent selection and communication as a cooperative game with task-conditioned net utility U(C∣x)=V(C∣x)− ∑ i∈C c i , separating coalition-level costs from agent activation costs. We propose a marginal-value activation rule and greedy router, extend the model to optimize communication edges with per-edge costs, and use estimated Shapley values to predict which agents are worth contacting before and during execution. We connect the problem to submodular maximization and prove two limited guarantees: a curvature-refined bound for a monotone, cardinality-constrained special case, and a tight 1/2 -approximation, with a correction for signed objectives, for an unconstrained non-monotone case via double greedy. Neither guarantee applies directly to the main router, which remains a heuristic. We also prove a Shapley-submodularity sandwich bound linking the error of marginal-value routing to a per-agent diminishing-returns quantity. In synthetic experiments, greedy routing achieves 99.5 of brute-force-optimal utility while activating 1.96 of 8 agents on average, compared with 38.8 for full broadcast. Performance is robust to activation cost and redundancy weight but falls to 66 under strong violations of submodularity or noisy value estimates. We distinguish the framework from Shapley pricing, hedonic coalition formation, and communication-graph pruning, and propose evaluation on real multi-agent LLM benchmarks. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Theoretical Economics (econ.TH) Cite as: arXiv:2608.07532 [cs.AI]   (or arXiv:2608.07532v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2608.07532 Focus to learn more Submission history From: Mojtaba Eslami [view email] [v1] Fri, 24 Jul 2026 19:25:21 UTC (27 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.LG econ econ.TH References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)