# Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems

arXiv: https://arxiv.org/abs/2606.07552 · HTML: https://mlsanity.com/paper/2606.07552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 22 of its 24 references that are in the map.
- First posted on arXiv 22 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 22 of 22)

- [Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers](https://mlsanity.com/paper/2603.07670/) (2026)
- [Welfare Diplomacy: Benchmarking Language Model Cooperation](https://mlsanity.com/paper/2310.08901/) (2023)
- [Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy](https://mlsanity.com/paper/2407.06813/) (2024)
- [The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?](https://mlsanity.com/paper/2305.07970/) (2023)
- [The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents](https://mlsanity.com/paper/2605.08060/) (2026)
- [Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games](https://mlsanity.com/paper/2410.21359/) (2024)
- [Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy](https://mlsanity.com/paper/2508.07485/) (2025)
- [Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games](https://mlsanity.com/paper/2604.09502/) (2026)
- [Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust](https://mlsanity.com/paper/2507.02197/) (2025)
- [Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors](https://mlsanity.com/paper/2603.21398/) (2026)
- [DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy](https://mlsanity.com/paper/2506.09655/) (2025)
- [Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?](https://mlsanity.com/paper/2512.06867/) (2025)
- [Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics](https://mlsanity.com/paper/2508.18600/) (2025)
- [Large language models replicate and predict human cooperation across experiments in game theory](https://mlsanity.com/paper/2511.04500/) (2025)
- [Benevolent Dictators? On LLM Agent Behavior in Dictator Games](https://mlsanity.com/paper/2511.08721/) (2025)
- [Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy](https://mlsanity.com/paper/2512.18292/) (2025)
- [Training Generalizable Collaborative Agents via Strategic Risk Aversion](https://mlsanity.com/paper/2602.21515/) (2026)
- [CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V](https://mlsanity.com/paper/2604.07733/) (2026)
- [Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees](https://mlsanity.com/paper/2604.14386/) (2026)
- [Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.05183/) (2026)
- [LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo](https://mlsanity.com/paper/2604.05681/) (2026)
- [Statistical Properties of the King Wen Sequence: An Anti-Habituation Structure That Does Not Improve Neural Network Training](https://mlsanity.com/paper/2604.09234/) (2026)

## Abstract (arXiv)

Large language models exhibit a risk-averse "turtle" bias as strategic agents. We show that injecting a symbolic reasoning framework as a per-round reflective prompt into one agent acts as a small perturbation whose consequences are not per-decision but emergent: the agent's risk posture is unchanged in isolation, yet over a campaign of accumulating memory and multi-agent interaction the conditions settle into distinct, condition-associated winner ecosystems. In a 7-player Warring States Diplomacy variant (61 games, 6 conditions), the winner distribution differs sharply across the four primary conditions (41 games; permutation omnibus p approximately 0.001): control -> Yan (7/11); I-Ching yarrow -> Yan/Chu co-dominance with Qin fully suppressed (0/10); Tarot -> Qin (5/10); scrambled-text ablation -> Qi (5/10). The scrambled->Qi attractor is robust (vs. pooled and control alone, p = 0.006 and 0.012); tarot->Qin is denominator-dependent (0.006 pooled, 0.064 vs. control). Han never wins and shows no survival difference (Fisher p = 1.0); neither framework's content predicts actions (chi-squared p = 0.95 hexagram, 0.69 Tarot). A memory-free decision-isolation probe (960 calls) shows the process does not change the agent's risk posture in isolation (Friedman p = 0.45; I-Ching p = 0.60; Tarot perturbs move content but not risk, p = 0.021). A 2x2 factorial separating yarrow's decision-time and learning-time components reveals a non-additive interaction: each alone freezes the board (50-60% stalemates), combined they produce zero (permutation p ~ 5e-5). Testing relocates Qin suppression to rival (Chu) expansion governed by campaign memory depth, not the oracle (p = 0.55). We present this as an observation paper: agent-level framework choice produces distinctive, non-additive system-level consequences, transmitted through emergent memory and multi-agent dynamics, not per-decision effects.