# Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry

arXiv: https://arxiv.org/abs/2607.11053 · HTML: https://mlsanity.com/paper/2607.11053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 68 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 30 of 36)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities](https://mlsanity.com/paper/2311.10227/) (2023)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences](https://mlsanity.com/paper/2107.08285/) (2021)
- [Honesty Is the Best Policy: Defining and Mitigating AI Deception](https://mlsanity.com/paper/2312.01350/) (2023)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [Re-evaluating Theory of Mind evaluation in large language models](https://mlsanity.com/paper/2502.21098/) (2025)
- [Common Ground Tracking in Multimodal Dialogue](https://mlsanity.com/paper/2403.17284/) (2024)
- [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025)
- [How RL Agents Behave When Their Actions Are Modified](https://mlsanity.com/paper/2102.07716/) (2021)
- [Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective](https://mlsanity.com/paper/2305.17760/) (2023)
- [Frictional Agent Alignment Framework: Slow Down and Don't Break Things](https://mlsanity.com/paper/2505.19428/) (2025)
- [Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World](https://mlsanity.com/paper/2404.00246/) (2024)
- [MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models](https://mlsanity.com/paper/2406.07736/) (2024)
- [Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories](https://mlsanity.com/paper/1906.05518/) (2019)
- [Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation](https://mlsanity.com/paper/2504.16060/) (2025)
- [MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games](https://mlsanity.com/paper/2602.24188/) (2026)
- [Are LLMs good pragmatic speakers?](https://mlsanity.com/paper/2411.01562/) (2024)
- [Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes](https://mlsanity.com/paper/2509.05882/) (2025)
- [Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues](https://mlsanity.com/paper/2410.19301/) (2024)
- [Evidence and plausibility in neighborhood structures](https://mlsanity.com/paper/1307.1277/) (2013)
- [DiPT: Enhancing LLM reasoning through diversified perspective-taking](https://mlsanity.com/paper/2409.06241/) (2024)

## Abstract (arXiv)

Fruitful collaborations rely on cooperative communications, including of contextual cues to incorporate into reasoning. The increasing use of LLMs in collaborative and agentic pipelines raises questions about the extent to which they exhibit these pragmatic capabilities, especially in scenarios where they may not have access to the same information as their collaborators. In this paper, we perform a novel investigation into the pragmatic reasoning capabilities of LLMs in a multi-party collaborative task under partial information conditions. We formalize a notion of collaborative epistemic asymmetry that explicitly connects objective task success to Grice's cooperative principle and empirically assess various LLMs' abilities to act cooperatively as both speakers and listeners, including both prompting and post-training strategies. Our results show that while LLMs exhibit certain pragmatic capabilities in collaborative settings, and these can be elicited through prompting and post-training, they still face challenges in pragmatic communication with incomplete information, and that certain failure modes do correlate with floutings of Grice's maxims that go unrecognized.