cs.MAJun 2, 2026

Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions

Authors: Aliakbar Mehdizadeh, Martin Hilbert

Organizations: Department of Communication University of California, Davis

Abstract

How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choices interact in a way that flips the sign of memory's effect on coordination. Across 432 simulation runs of a networked Naming Game on eight fixed 16-agent topologies, we vary memory depth and network structure. Longer memory slows the time to reach steady state in decentralized networks but accelerates it in centralized ones; the same parameter pushes the system in opposite directions depending on topology. Critically, "faster settling" in centralized networks means locking in to a fragmented plateau more quickly, not reaching system-wide consensus, which can be used to generate diverging opinions. We further document a memory-mediated speed-unity trade-off: centralized networks consistently preserve more competing conventions than decentralized networks, but their settling speed depends sharply on memory. At the agent level, within-network analyses show that high-betweenness bridges suffer a brokerage penalty while agents in locally clustered neighborhoods achieve higher coordination success. Finally, in search of analytically tractable generative mechanisms, we find that agents' choices are well captured by Fictitious Play, indicating belief-based rather than reward-based adaptation. The practical implication: memory depth and communication topology should be co-designed, not optimized in isolation.

Explore similar work

CardsList
Jun 30, 2026cs.AI

From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents

How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study five memory architectures across varying channel configurations with LLM agents and find that memory architecture matters more than channel capacity. Agents with a persistent private notebook benefit from surplus channel capacity and avoid the high-capacity collapse seen in stateless agents, achieving the most reliable coordination (0.867±0.0230.867 \pm 0.023 at capacity = 25). Stateless agents peak at moderate capacity and then degrade as the vocabulary grows beyond what a rolling context window can track The notebook externalizes learned conventions, freeing agents from having to re-derive codes each round. An information bottleneck-inspired argument predicts an optimal capacity equal to the number of objects. Instead, the bottleneck (capacity = 8) proves to be a fragility point, and surplus capacity is generally better. We show that channel capacity alone cannot predict coordination; memory architecture determines whether agents turn interaction history into stable conventions, and both dimensions are needed to understand how signals become language.
Yashar Talebirad, Eden Redman, Ali Parsaee +1
Large Language Model AgentsAgent MemoryInteraction HistoryBottlenecksChannel State Information
AskPDF
May 21, 2026cs.MA

Self-Evolving Multi-Agent Systems via Decentralized Memory

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized repository shared across agents, incurring communication and coordination overhead, raising privacy concerns, and collapsing agent diversity. We propose DecentMem, a decentralized memory framework in which each agent maintains its own dual-pool memory -- an exploitation pool of consolidated past trajectories and an exploration pool of LLM-generated candidates for unseen contexts. The two pools are reweighted online based on stage-wise feedback from an LLM-as-a-judge. Theoretically, we prove that this design guarantees global reachability of the solution space and achieves O(log⁡T)O(\log T) cumulative regret, matching the stochastic bandit lower bound up to constants. In practice, across three MAS frameworks (AutoGen, DyLAN, AgentNet), three Qwen3 backbones (4B/8B/14B), two Gemma4 backbones (E2B/E4B) and five benchmarks spanning math, code, QA, and embodied tasks, DecentMem improves average accuracy by up to 23.8% over the strongest centralized memory baseline and by up to 52.5% over the no-memory baseline, while reducing token usage by up to 49%.
Guangya Hao, Yunbo Long, Zhuokai Zhao
Agent MemorySelf-Evolving AgentsMemforestDecentralizationOutput and Model Diversity
AskPDF
Aug 3, 2026physics.soc-ph

Microscopic dynamics of consensus formation in multi-agent LLM Naming Games

Decentralized populations of Large Language Model (LLM) agents can spontaneously reach consensus on shared conventions, yet the microscopic mechanisms by which their internal stochasticity shapes macroscopic ordering remain unexplored. We study a minimal LLM Naming Game in which the listener's decision is a single-token LLM call at decoding temperature TT, replacing the inventory check of the deterministic Naming Game. Each interaction decomposes into an in-inventory and an out-inventory channel with conditional rates π(T) ⁣≡ ⁣P(YES∣w∈Pj)π(T)\!\equiv\!P(\text{YES}\mid w\in P_j) and φ(T) ⁣≡ ⁣P(YES∣w∉Pj)φ(T)\!\equiv\!P(\text{YES}\mid w\notin P_j), whose balance controls an ordering-disordering drift. A mean-field theory of the two-rate dynamics yields an analytical ordering condition that generalizes the consensus threshold of the stochastic Naming Game to a critical line in the (π,φ)(π,φ) plane. Across three open-weight architectures, consensus is always reached, but through three distinct listener regimes: permissive (repaint-noise dominated), near-deterministic, and conservative (missed-collapse dominated). The effective finite-size exponent β(T)β(T) in tconv ⁣∼ ⁣Nβt_{\rm conv}\!\sim\!N^β shifts with temperature, and the temperature-sensitivity αα in tc ⁣∼ ⁣eαTt_c\!\sim\!e^{αT} ranges from ≈ 0.67{\approx}\,0.67 to ≈ 0{\approx}\,0 across architectures. Decoding temperature thus emerges as an architecture-dependent control parameter for decentralized LLM populations, quantitatively characterized by the statistical-physics toolkit.
Cristiano De Nobili, Vijayasri Iyer, Alessandro Codello +1
Multi-Agent Large Language Model SystemsConsensus
AskPDF