Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

• URL: http://arxiv.org/abs/2605.01750v1
• Date: Sun, 03 May 2026 07:12:14 GMT
• Title: Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
• Abstract summary: Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose.<n>Current multi-agent Large Language Model (LLM) benchmarks focus on static, one-shot tasks.<n>We introduce an iterated, multi-turn negotiation game in which two agents allocate shared resources toward private projects with verifiable jointly optimal outcomes.
• Score: 2.5089149965583086
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose. While static grounding maps language to a shared, externally observable context, dynamic grounding is a joint activity where meaning is negotiated through interaction. Current multi-agent Large Language Model (LLM) benchmarks focus on static, one-shot tasks, overlooking the ability to repair grounding breakdowns across turns. We introduce an iterated, multi-turn negotiation game in which two agents allocate shared resources toward private projects with verifiable jointly optimal outcomes. While individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across open- and closed-source models. Our investigation reveals four failure modes: (1) coordination degrades when shared interaction history is absent; (2) yet accumulated context can itself become a liability through stubborn anchoring, where initial proposals are treated as axiomatic rather than negotiable; (3) a reliance on perfunctory fairness (equal resource splits) over reward-maximizing coordination; and (4) failures in referential binding, where agents lose track of commitments across turns. These results highlight dynamic grounding as a critical and understudied axis of multi-agent coordination. Our framework decomposes the coordination gap into measurable components: the oracle baseline establishes that the gap is not attributable to individual reasoning limitations; the no-talk baseline establishes that communication is necessary; and a full-transparency intervention establishes that information exchange alone is insufficient: the bottleneck lies in the interactive processes of joint plan formation, commitment, and execution that constitute dynamic grounding.

Related papers

• Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks [48.90302419915548]
  Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in smart factories, warehouses, and service robotics.<n>We propose LDT-Coord, a networked coordination framework built upon a lightweight digital twin (DT)<n>Specifically, each agent independently selects its intended action and reports both the action decision and a structured temporal constraint over shared resources to the DT server.
  arXiv  Detail & Related papers  (2026-07-10T12:10:31Z)
• Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games [4.3857499122259815]
  This study builds on work showing that cheap-talk channels enable cooperation in multi-agent coordination games.<n>We investigate two vulnerability classes in a 4-player Stag Hunt across six model families and 720 trials.<n>We identify two stable behavioral archetypes that replicate across all model cohorts: Defection-Prone models that switch permanently after betrayal, and Cooperation-Persistent models that continue cooperating at significant individual cost.
  arXiv  Detail & Related papers  (2026-06-05T19:06:44Z)
• Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue [9.790389620810933]
  Communication can bridge this gap by allowing agents to share observations and align their world models.<n>We extend PARTNR, a benchmark for collaborative household robotics, with a natural-language dialogue channel that enables two agents with partial observability to communicate.<n>Our experiments reveal that dialogue reduces action conflicts 40 to 83 percentage points but degrades task success relative to silent coordination.
  arXiv  Detail & Related papers  (2026-05-13T02:48:14Z)
• The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search [2.435326482104274]
  Coordination is necessary to share beliefs to aid in task completion, but communication costs bandwidth, introduces latency, and if done poorly, can degrade collective reasoning.<n>This tension is especially acute in bandwidth-constrained deployments such as distributed sensing networks, autonomous reconnaissance, and collaborative cyber defense.<n>We formalize this distinction and show it is not detectable from coordination metrics alone such as Jensen-Shannon Divergence or rate to consensus.
  arXiv  Detail & Related papers  (2026-05-07T22:07:25Z)
• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration [18.250351934101463]
  DR. WELL is a decentralized neurosymbolic framework for cooperative multi-agent planning.<n>Agents propose candidate roles and commit to a joint allocation under consensus and environment constraints.<n>Each agent independently generates and executes a symbolic plan for its role without revealing detailed trajectories.
  arXiv  Detail & Related papers  (2025-11-06T18:37:18Z)
• Learning to Interact in World Latent for Team Coordination [53.51290193631586]
  This work presents a novel representation learning framework, interactive world latent (IWoL), to facilitate team coordination in multi-agent reinforcement learning (MARL)<n>Our key insight is to construct a learnable representation space that jointly captures inter-agent relations and task-specific world information by directly modeling communication protocols.<n>Our representation can be used not only as an implicit latent for each agent, but also as an explicit message for communication.
  arXiv  Detail & Related papers  (2025-09-29T22:13:39Z)
• Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models [41.95288786980204]
  Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter- module communication. We present a framework for training large language models as collaborative agents to enable coordinated behaviors in cooperative MARL. A propagation network transforms broadcast intentions into teammate-specific communication messages, sharing relevant goals with designated teammates.
  arXiv  Detail & Related papers  (2024-07-17T13:14:00Z)
• Asynchronous Message-Passing and Zeroth-Order Optimization Based Distributed Learning with a Use-Case in Resource Allocation in Communication Networks [11.182443036683225]
  Distributed learning and adaptation have received significant interest and found wide-ranging applications in machine learning signal processing.<n>This paper specifically focuses on a scenario where agents collaborate towards a common task.<n>Agents, acting as transmitters, collaboratively train their individual policies to maximize a global reward.
  arXiv  Detail & Related papers  (2023-11-08T11:12:27Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification [77.59549450705384]
  In dialog system, dialog act recognition and sentiment classification are two correlative tasks. Most of the existing systems either treat them as separate tasks or just jointly model the two tasks. We propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks.
  arXiv  Detail & Related papers  (2020-08-16T14:13:32Z)

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.