EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium

• URL: http://arxiv.org/abs/2605.09278v1
• Date: Sun, 10 May 2026 03:04:12 GMT
• Title: EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
• Abstract summary: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning.<n>A single corrupted entry can contaminate the downstream memory-augmented reasoning, and debate alone fails to filter such errors.<n>We propose EquiMem, an inference-time calibration mechanism that quantifies each update algorithmically against the shared memory state.
• Score: 10.71445877501096
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single corrupted entry can contaminate the downstream memory-augmented reasoning, and debate alone fails to filter such errors. Existing safeguards filter entries via heuristics or LLM-based validation, yet they rely on AI judgments that share the same failure modes and overlook the cross-agent dynamics of MAD. We address this gap by formulating memory updating in MAD as a zero-trust memory game, in which no agent is assumed honest and the game's equilibrium serves as an indicator of optimal memory trust. Guided by this equilibrium, we propose EquiMem, an inference-time calibration mechanism that quantifies each update algorithmically against the shared memory state, using agents' existing retrieval queries and traversal paths as evidence rather than soliciting any LLM judgment. EquiMem instantiates calibration for both embedding- and graph-based memory, and across diverse benchmarks, MAD frameworks, and memory architectures, it consistently outperforms existing safeguards, remains robust under adversarial agents, and incurs negligible inference overhead.

Related papers

• Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner [55.80248281761638]
  multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning.<n>We propose DG-Mem, a dual-grained agentic memory framework that augments a frozen MLLM with a non- externally stored memory built once from training-time rollouts and consulted read-only at test time.
  arXiv  Detail & Related papers  (2026-08-24T13:56:01Z)
• Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents [97.19033877543522]
  We present a controlled harness evaluation of memory substrates for memory-augmented agents.<n>We instrument 26 performance and efficiency metrics under a unified harness.<n>These findings motivate substrate routing as a necessary component of adaptive agent memory systems.
  arXiv  Detail & Related papers  (2026-08-15T03:29:48Z)
• $Σ$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems [37.51924580838879]
  Existing memory systems preserve interaction content rather than modeling which agents can be trusted and under what conditions.<n>We introduce $$-Mem, an online reliability memory that records historical competence evidence for individual peers and peer relationship evidence across the peer set.<n>$$-Mem provides a general write-and-read interface: the same memory can be used for residual steering of a central model, response-free peer routing, or reliability-weighted voting.
  arXiv  Detail & Related papers  (2026-07-30T10:05:50Z)
• MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection [15.403262505444454]
  We propose a post-hoc causal memory auditing framework for large language model agents.<n>MemAudit substantially reduces attack success rates under realistic post-hoc auditing scenarios.
  arXiv  Detail & Related papers  (2026-05-22T15:03:13Z)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory [7.707732051915869]
  Diagnosing agentic memory systems reveals that memory improves reasoning on clean inputs but amplifies reliance on spurious patterns when they are present.<n>We propose CAMEL, a plug-and-play calibration method that operates across diverse memory architectures at both write and retrieval time.<n>Overall, CAMEL offers a principled and lightweight solution toward more reliable agentic memory deployment.
  arXiv  Detail & Related papers  (2026-05-10T05:04:13Z)
• Belief Memory: Agent Memory Under Partial Observability [56.41506249481312]
  We propose BeliefMem, which shifts the memory paradigm from committing to a single conclusion per observation to retaining multiple candidate conclusions with their probabilities.<n> BeliefMem preserves the uncertainty that the deterministic paradigm discards, enabling the agent to act with high confidence.<n> Empirical evaluations on LoCoMo and ALFWorld benchmarks show that, even with limited data, BeliefMem achieves the best average performance.
  arXiv  Detail & Related papers  (2026-05-07T02:03:13Z)
• Memory Centric Power Allocation for Multi-Agent Embodied Question Answering [49.3249799261475]
  Multi-agent embodied question answering (MA-EQA) aims to query robot teams on what they have seen over a long horizon.<n>To cope with this paradigm shift, we propose a quality of memory (QoM) model based on generative adversarial exam (GAE)<n>Then we propose memory centric power allocation (MCPA), which maximizes the QoM function under communication resource constraints.
  arXiv  Detail & Related papers  (2026-04-20T05:08:53Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation [16.57908722474221]
  Large language model (LLM)-based agents rely on memory mechanisms to reuse knowledge from past problem-solving experiences.<n>Existing approaches typically construct memory in a per-agent manner, tightly coupling stored knowledge to a single model's reasoning style.<n>We found that naively transferring memory between agents often degrades performance, as such memory entangles task-relevant knowledge with agent-specific biases.<n>We propose MemCollab, a collaborative memory framework that constructs agent-agnostic memory by contrasting reasoning trajectories generated by different agents on the same task.
  arXiv  Detail & Related papers  (2026-03-24T14:05:47Z)
• MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution [52.29303869050117]
  Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction.<n>MemMA is a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths.
  arXiv  Detail & Related papers  (2026-03-19T10:15:59Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory [31.673865459672285]
  Large Language Model (LLM) agents use memory to learn from past interactions.<n>An adversary can inject seemingly harmless records into an agent's memory to manipulate its future behavior.<n>A-MemGuard is the first proactive defense framework for LLM agent memory.
  arXiv  Detail & Related papers  (2025-09-29T16:04:15Z)
• SEDM: Scalable Self-Evolving Distributed Memory for Agents [23.182291416527764]
  SEDM is a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component.<n>We show that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines.<n>Results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration.
  arXiv  Detail & Related papers  (2025-09-11T14:37:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.