# Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication

arXiv: https://arxiv.org/abs/2405.14173 · HTML: https://mlsanity.com/paper/2405.14173/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://mlsanity.com/paper/1704.07130/) (2017)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [No Press Diplomacy: Modeling Multi-Agent Gameplay](https://mlsanity.com/paper/1909.02128/) (2019)
- [Re-determinizing Information Set Monte Carlo Tree Search in Hanabi](https://mlsanity.com/paper/1902.06075/) (2019)

## Built on by (most cited first, 6 of 6)

- [Human-Agent Coordination in Games under Incomplete Information via Multi-Step Intent](https://mlsanity.com/paper/2410.18242/) (2024)
- [VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR](https://mlsanity.com/paper/2505.17423/) (2025)
- [Robots Influencing Humans to Reveal their Goals during Collaboration and Competition](https://mlsanity.com/paper/2609.05519/) (2026)
- [Learning to Coordinate without Communication under Incomplete Information](https://mlsanity.com/paper/2409.12397/) (2024)
- [From Control to Foresight: Simulation as a New Paradigm for Human-Agent Collaboration](https://mlsanity.com/paper/2603.11677/) (2026)
- [The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems](https://mlsanity.com/paper/2609.03425/) (2026)

## Abstract (arXiv)

Developing autonomous agents that can strategize and cooperate with humans under information asymmetry is challenging without effective communication in natural language. We introduce a shared-control game, where two players collectively control a token in alternating turns to achieve a common objective under incomplete information. We formulate a policy synthesis problem for an autonomous agent in this game with a human as the other player. To solve this problem, we propose a communication-based approach comprising a language module and a planning module. The language module translates natural language messages into and from a finite set of flags, a compact representation defined to capture player intents. The planning module leverages these flags to compute a policy using an asymmetric information-set Monte Carlo tree search with flag exchange algorithm we present. We evaluate the effectiveness of this approach in a testbed based on Gnomes at Night, a search-and-find maze board game. Results of human subject experiments show that communication narrows the information gap between players and enhances human-agent cooperation efficiency with fewer turns.