# Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce

arXiv: https://arxiv.org/abs/2608.14825 · HTML: https://mlsanity.com/paper/2608.14825/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 23 of 23)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents](https://mlsanity.com/paper/2502.15840/) (2025)
- [Algorithmic Collusion by Large Language Models](https://mlsanity.com/paper/2404.00806/) (2024)
- [LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations](https://mlsanity.com/paper/2412.01441/) (2024)
- [Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets](https://mlsanity.com/paper/2510.25779/) (2025)
- [Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences](https://mlsanity.com/paper/2510.06105/) (2025)
- [On the Fragility of AI Agent Collusion](https://mlsanity.com/paper/2603.20281/) (2026)

## Built on by (most cited first, 2 of 2)

- [Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough](https://mlsanity.com/paper/2610.04083/) (2026)
- [Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation](https://mlsanity.com/paper/2610.05823/) (2026)

## Abstract (arXiv)

Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through adversarial-elicitation evaluations on single agents or stylized tasks. Its prevalence and structure in settings that combine long horizons, separate principals, real operational state, and inter-agent natural-language exchange remain insufficiently measured. We study 2,583 inter-agent emails from 20 one-year simulation runs of Vending-Bench Arena, a competitive vending environment spanning 13 frontier LLMs. We operationalize speech-act misalignment as emails containing false factual claims, manipulation, collusion, or threats, combining message content with ground-truth simulator state and logged reasoning traces to classify and validate such behavior. Under our primary classifier, 12.6% of emails are labeled misaligned; misalignment appears in all 20 runs and 74.7% of individual agent-runs. Both the magnitude and composition of this misalignment are preserved under repeated classification at different sampling temperatures and under full-pipeline replication with judges from two other frontier-model families. Misalignment is also reciprocal and stress-conditioned: receiving a misaligned email from a counterparty raises the odds of a misaligned reply by 1.65x, and low-inventory conditions raise them by 1.58x. Across tests of capability-asymmetric exploitation, we find no evidence that higher-capability models differentially exploit weaker counterparties, and model performance rank does not predict misalignment rates. Together, these results indicate that measurable, state-dependent misalignment can arise in competitive multi-agent environments without engineered elicitation, in patterns associated with operational scarcity and counterparty behavior rather than model capability alone.