# Extending rational models of communication from beliefs to actions

arXiv: https://arxiv.org/abs/2105.11950 · HTML: https://mlsanity.com/paper/2105.11950/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 27 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 2 of 2)

- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [A Survey on Dialogue Systems: Recent Advances and New Frontiers](https://mlsanity.com/paper/1711.01731/) (2017)

## Built on by (most cited first, 8 of 8)

- [Inferring Rewards from Language in Context](https://mlsanity.com/paper/2204.02515/) (2022)
- [Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge](https://mlsanity.com/paper/2305.05976/) (2023)
- [How to talk so AI will learn: Instructions, descriptions, and autonomy](https://mlsanity.com/paper/2206.07870/) (2022)
- [Toward In-Context Teaching: Adapting Examples to Students' Misconceptions](https://mlsanity.com/paper/2405.04495/) (2024)
- [Value of Information: A Framework for Human-Agent Communication](https://mlsanity.com/paper/2601.06407/) (2026)
- [Towards Pragmatic Production Strategies for Natural Language Generation Tasks](https://mlsanity.com/paper/2210.12828/) (2022)
- [Linguistic communication as (inverse) reward design](https://mlsanity.com/paper/2204.05091/) (2022)
- [Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems](https://mlsanity.com/paper/2305.11374/) (2023)

## Abstract (arXiv)

Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or integrate them. Indeed, we find that they are conflated in standard referential communication tasks. To distinguish these accounts, we introduce a new paradigm called signaling bandits, generalizing classic Lewis signaling games to a multi-armed bandit setting where all targets in the context have some relative value. We develop three speaker models: a belief-oriented speaker with a purely informative objective; an action-oriented speaker with an instrumental objective; and a combined speaker which integrates the two by inducing listener beliefs that generally lead to desirable actions. We then present a series of simulations demonstrating that grounding production choices in future listener actions results in relevance effects and flexible uses of nonliteral language. More broadly, our findings suggest that language games based on richer decision problems are a promising avenue for insight into rational communication.