# MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games Source: [MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games]() Collection index: [llms.txt]() Data updated: 2026-03-21T06:00:01.553Z Authors: Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang Published: 2026-03-09T23:36:32.000Z ## Abstract Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates and makes rankings unreliable across repeated tournaments. Prompt choice worsens this further by producing different effective policies. We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework that optimizes inference-time context by coupling retention and exploration. Retention maintains a persistent memory bank that stores structured insights from self-play trajectories and injects them as priors during later play. Exploration runs tournament-style prompt evolution with uncertainty-aware selection via TrueSkill, and uses prioritized replay to revisit rare and decisive states. Across five text-based games, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 44.3% for Qwen-2.5-7B-Instruct, using $2,000$ self-play games per task. Run-to-run variance also drops, giving more stable rankings across prompt variations. These results suggest that multi-agent LLM game performance and robustness have substantial room for improvement through context optimization. MEMO achieves the largest gains in negotiation and imperfect-information games, while RL remains more effective in perfect-information settings. All code is open-source and available here: https://github.com/openverse-ai/MEMO ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-turn Strategic Gameplay on Multi-turn Game Suite](): Multi-turn Strategic Gameplay; Multi-turn Game Suite (SimpleNegotiation, TwoDollar, KuhnPoker, Briscola, SimpleTak); SimpleNegotiation Win Rate: 54.9. - [Strategic Game Playing on TextArena SPIN-Bench](): Strategic game playing; TextArena SPIN-Bench; Win Rate (Simple Negotiation): 54.9. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()