Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems
Augustin Chan
Why It Matters
What makes this one worth your time
Understanding how symbolic reasoning affects multi-agent interactions could inform the design of more robust and adaptive AI systems.
Symbolic reasoning frameworks in multi-agent systems lead to emergent ecosystem dynamics.
Summary
The paper investigates the effects of introducing symbolic reasoning frameworks into multi-agent systems using large language models, observing emergent ecosystem dynamics and memory-mediated interactions rather than per-decision changes.
Key contributions
- Demonstrates emergent ecosystem dynamics in multi-agent systems with symbolic reasoning.
- Provides empirical evidence of condition-associated winner ecosystems in a strategic game setting.
Notable insights
- Symbolic reasoning frameworks can lead to emergent, memory-mediated dynamics in multi-agent systems.
- The impact of reasoning frameworks is not immediate but accumulates over time through interactions.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2606.07552v2 Announce Type: replace-cross Abstract: 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.