# Planning, Inference and Pragmatics in Sequential Language Games

arXiv: https://arxiv.org/abs/1805.11774 · HTML: https://mlsanity.com/paper/1805.11774/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2018.

## Built on by (most cited first, 12 of 12)

- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [On the Critical Role of Conventions in Adaptive Human-AI Collaboration](https://mlsanity.com/paper/2104.02871/) (2021)
- [Modeling Cross-Cultural Pragmatic Inference with Codenames Duet](https://mlsanity.com/paper/2306.02475/) (2023)
- [Reference-Centric Models for Grounded Collaborative Dialogue](https://mlsanity.com/paper/2109.05042/) (2021)
- [Draw Me a Flower: Processing and Grounding Abstraction in Natural Language](https://mlsanity.com/paper/2106.14321/) (2021)
- [Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches](https://mlsanity.com/paper/2211.08371/) (2022)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Asking More Informative Questions for Grounded Retrieval](https://mlsanity.com/paper/2311.08584/) (2023)
- [Symbolic Planning and Code Generation for Grounded Dialogue](https://mlsanity.com/paper/2310.17140/) (2023)
- [CRAFT: Grounded Multi-Agent Coordination Under Partial Information](https://mlsanity.com/paper/2603.25268/) (2026)
- [Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog](https://mlsanity.com/paper/2507.14063/) (2025)
- [HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs](https://mlsanity.com/paper/2603.20299/) (2026)

## Abstract (arXiv)

We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the partner's private information from the partner's messages, (ii) generate messages that are most likely to help with the goal, and (iii) reason pragmatically about the partner's strategy. We propose a model that captures all three characteristics and demonstrate their importance in capturing human behavior on a new goal-oriented dataset we collected using crowdsourcing.