Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

Computer Science > Cryptography and Security [Submitted on 9 Jun 2026] Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel, Kawser Wazed Nafi, Foutse Khomh Large Language Models (LLMs) in multi-turn interactions maintain evolving context rather than generating isolated responses, making them vulnerable to prompt-injection and context-poisoning attacks in which locally plausible adversarial fragments gradually distort reasoning trajectories. Existing defenses mainly filter individual outputs and often ignore context evolution across turns, leaving long-horizon reasoning exposed. Although the Model Context Protocol (MCP) standardizes context exchange and tool invocation, it functions as a passive routing layer and does not enforce contextual stability. To address these limitations, we introduce the Game-Theoretic Secure Model Context Protocol (GT-MCP), a controller-driven multi-agent method that treats context management as a closed-loop dynamical process. GT-MCP coordinates three heterogeneous LLM agents and selects outputs through a trust function that jointly evaluates causal consistency against a validated context graph, semantic agreement among agents, and distributional drift over time. When instability is detected, a rollback-based self-healing mechanism restores the validated context and prevents unsupported fragments from propagating. Empirical evaluation over 500 interaction turns under an adaptive adversarial threat model shows that contextual drift remains bounded in 99.6% of turns, with recovery required in only 0.4%. Per-turn utility remains tightly concentrated, with median = -0.19, P05 = -0.72, and P95 = 0.30; severe degradation below -1 occurs in only 0.4% of cases, and no injection attempt succeeds at the controller level. Selected outputs maintain stable win rates above 98%, and computational overhead remains predictable, with latency per token = 1.63e-3 s. Subjects: Cryptography and Security (cs.CR); Multiagent Systems (cs.MA) Cite as: arXiv:2606.10322 [cs.CR]   (or arXiv:2606.10322v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.10322 Focus to learn more Submission history From: Saeid Jamshidi [view email] [v1] Tue, 9 Jun 2026 02:18:44 UTC (4,469 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.MA 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?)