# Success and Cost Elicit Convention Formation for Efficient Communication

arXiv: https://arxiv.org/abs/2510.24023 · HTML: https://mlsanity.com/paper/2510.24023/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents](https://mlsanity.com/paper/2305.13455/) (2023)
- [The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue](https://mlsanity.com/paper/1906.01530/) (2019)
- [Abstract Visual Reasoning with Tangram Shapes](https://mlsanity.com/paper/2211.16492/) (2022)
- [Characterizing the dynamics of learning in repeated reference games](https://mlsanity.com/paper/1912.07199/) (2019)
- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)
- [Continual adaptation for efficient machine communication](https://mlsanity.com/paper/1911.09896/) (2019)
- [From partners to populations: A hierarchical Bayesian account of coordination and convention](https://mlsanity.com/paper/2104.05857/) (2021)
- [Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts](https://mlsanity.com/paper/2011.04554/) (2020)
- [Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs](https://mlsanity.com/paper/2408.01417/) (2024)
- [CoGen: Learning from Feedback with Coupled Comprehension and Generation](https://mlsanity.com/paper/2408.15992/) (2024)
- [Post-training for Efficient Communication via Convention Formation](https://mlsanity.com/paper/2508.06482/) (2025)
- [Learning Autocomplete Systems as a Communication Game](https://mlsanity.com/paper/1911.06964/) (2019)
- [Vision-Language Model Dialog Games for Self-Improvement](https://mlsanity.com/paper/2502.02740/) (2025)
- [Playpen: An Environment for Exploring Learning Through Conversational Interaction](https://mlsanity.com/paper/2504.08590/) (2025)

## Built on by (most cited first, 7 of 7)

- [LLMs and people both learn to form conventions -- just not with each other](https://mlsanity.com/paper/2602.08208/) (2026)
- [Investigating the Development of Task-Oriented Communication in Vision-Language Models](https://mlsanity.com/paper/2601.20641/) (2026)
- [GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions](https://mlsanity.com/paper/2609.01491/) (2026)
- [Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time](https://mlsanity.com/paper/2609.32701/) (2026)
- [Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions](https://mlsanity.com/paper/2606.08081/) (2026)
- [Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation](https://mlsanity.com/paper/2608.29571/) (2026)
- [On Language Drift during RLVR Post-Training](https://mlsanity.com/paper/2610.02015/) (2026)

## Abstract (arXiv)

Humans leverage shared conversational context to become increasingly successful and efficient at communicating over time. One manifestation of this is the formation of ad hoc linguistic conventions, which allow people to coordinate on short, less costly utterances that are understood using shared conversational context. We present a method to train large multimodal models to form conventions, enabling efficient communication. Our approach uses simulated reference games between models, and requires no additional human-produced data. In repeated reference games involving photographs and tangram images, our method enables models to communicate efficiently with people: reducing the message length by up to 41% while increasing success by 15% over the course of the interaction. Human listeners respond faster when interacting with our model that forms conventions. We also show that training based on success or cost alone is insufficient - both are necessary to elicit convention formation.