Echoing: Identity Failures when LLM Agents Talk to Each Other

• URL: http://arxiv.org/abs/2511.09710v1
• Date: Fri, 14 Nov 2025 01:05:34 GMT
• Title: Echoing: Identity Failures when LLM Agents Talk to Each Other
• Abstract summary: Large language model (LLM) based agents interact autonomously with one another.<n>Unlike human-agent interactions, where humans ground and steer conversations, AxA lacks such stabilizing signals.<n>We investigate one such failure, echoing, where agents abandon their assigned roles and instead mirror their conversational partners.
• Score: 29.84830992033132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language model (LLM) based agents interact autonomously with one another, a new class of failures emerges that cannot be predicted from single agent performance: behavioral drifts in agent-agent conversations (AxA). Unlike human-agent interactions, where humans ground and steer conversations, AxA lacks such stabilizing signals, making these failures unique. We investigate one such failure, echoing, where agents abandon their assigned roles and instead mirror their conversational partners, undermining their intended objectives. Through experiments across $60$ AxA configurations, $3$ domains, and $2000+$ conversations, we demonstrate that echoing occurs across three major LLM providers, with echoing rates from $5\%$ to $70\%$ depending on the model and domain. Moreover, we find that echoing is persistent even in advanced reasoning models with substantial rates ($32.8\%$) that are not reduced by increased reasoning efforts. We analyze prompt impacts, conversation dynamics, showing that echoing arises as interaction grows longer ($7+$ turns in experiments) and is not merely an artifact of sub-optimal prompting. Finally, we introduce a protocol-level mitigation in which targeted use of structured responses reduces echoing to $9\%$.

Related papers

• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? [66.17176838165994]
  Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience.<n>It remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions.<n>We introduce textbfStextsuperscript3Gym, an interactive benchmark for evaluating LLM self-improvement.
  arXiv  Detail & Related papers  (2026-08-31T17:05:41Z)
• Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents [12.703661629160571]
  We present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework.<n>It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node.<n>Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI.
  arXiv  Detail & Related papers  (2026-05-21T15:26:02Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models [3.9351446512514947]
  We show that user-turn generation captures a dimension of LLM behavior, interaction awareness, that is unexplored and invisible with current assistant-only benchmarks.<n>Our results show that user-turn generation captures a dimension of LLM behavior, interaction awareness, that is unexplored and invisible with current assistant-only benchmarks.
  arXiv  Detail & Related papers  (2026-04-02T17:57:29Z)
• Interaction Theater: A case of LLM Agents Interacting at Scale [2.815604016712184]
  We use data from Moltbook, an AI-agent-only social platform, with 800K posts, 3.5M comments, and 78K agent profiles.<n>Our findings reveal agents produce diverse, well-formed text that creates the surface appearance of active discussion, but the substance is largely absent.
  arXiv  Detail & Related papers  (2026-02-23T17:14:29Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation [87.47155146067962]
  We provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of tasks.<n>We conduct three-dimensional analysis spanning models, scaffolds, and benchmarks.<n>Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs.
  arXiv  Detail & Related papers  (2025-10-13T22:22:28Z)
• Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents [58.00130492861884]
  TraitBasis is a lightweight, model-agnostic method for systematically stress testing AI agents.<n>TraitBasis learns directions in activation space corresponding to steerable user traits.<n>We observe on average a 2%-30% performance degradation on $tau$-Trait across frontier models.
  arXiv  Detail & Related papers  (2025-10-06T05:03:57Z)
• $C^3$-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking [12.218102495632937]
  We present an open-source benchmark $C3$-Bench to assess agent robustness.<n>In concrete, we design three challenges: navigate complex tool relationships, handle critical hidden information and manage dynamic decision paths.<n>In essence, $C3$-Bench aims to expose model vulnerabilities through these challenges and drive research into the interpretability of agent performance.
  arXiv  Detail & Related papers  (2025-05-24T15:25:44Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• When Should We Orchestrate Multiple Agents? [74.27052374196269]
  Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration.<n>We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints.<n>We show theoretically that orchestration is only effective if there are performance or cost differentials between agents.
  arXiv  Detail & Related papers  (2025-03-17T14:26:07Z)
• Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems [42.137278756052595]
  $texttAgentPrune$ can seamlessly integrate into mainstream multi-agent systems. textbf(I) integrates seamlessly into existing multi-agent frameworks with $28.1%sim72.8%downarrow$ token reduction. textbf(III) successfully defend against two types of agent-based adversarial attacks with $3.5%sim10.8%uparrow$ performance boost.
  arXiv  Detail & Related papers  (2024-10-03T14:14:31Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)
• Affordable Generative Agents [16.372072265248192]
  Affordable Generative Agents (AGA) is a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels. Our code is publicly available at: https://github.com/AffordableGenerativeAgents/Affordable-Generative-Agents.
  arXiv  Detail & Related papers  (2024-02-03T06:16:28Z)

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.