# Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning

arXiv: https://arxiv.org/abs/2005.07064 · HTML: https://mlsanity.com/paper/2005.07064/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2020.

## Built on by (most cited first, 30 of 66)

- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [WARM: On the Benefits of Weight Averaged Reward Models](https://mlsanity.com/paper/2401.12187/) (2024)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [BOND: Aligning LLMs with Best-of-N Distillation](https://mlsanity.com/paper/2407.14622/) (2024)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [WARP: On the Benefits of Weight Averaged Rewarded Policies](https://mlsanity.com/paper/2406.16768/) (2024)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [LLM Harmony: Multi-Agent Communication for Problem Solving](https://mlsanity.com/paper/2401.01312/) (2024)
- [Language Model Alignment with Elastic Reset](https://mlsanity.com/paper/2312.07551/) (2023)
- [Emergent Discrete Communication in Semantic Spaces](https://mlsanity.com/paper/2108.01828/) (2021)
- [Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning](https://mlsanity.com/paper/2404.19409/) (2024)
- [Linking Emergent and Natural Languages via Corpus Transfer](https://mlsanity.com/paper/2203.13344/) (2022)
- [Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication](https://mlsanity.com/paper/2409.17348/) (2024)
- [Computational Language Acquisition with Theory of Mind](https://mlsanity.com/paper/2303.01502/) (2023)
- [LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models](https://mlsanity.com/paper/2405.21028/) (2024)
- [Diffusion Guided Language Modeling](https://mlsanity.com/paper/2408.04220/) (2024)
- [Learning to Mediate Disparities Towards Pragmatic Communication](https://mlsanity.com/paper/2203.13685/) (2022)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off](https://mlsanity.com/paper/2301.13083/) (2023)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Once Upon a Time: Interactive Learning for Storytelling with Small Language Models](https://mlsanity.com/paper/2509.15714/) (2025)
- [Dynamic population-based meta-learning for multi-agent communication with natural language](https://mlsanity.com/paper/2110.14241/) (2021)
- [Calibrate your listeners! Robust communication-based training for pragmatic speakers](https://mlsanity.com/paper/2110.05422/) (2021)
- [Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction](https://mlsanity.com/paper/2510.20411/) (2025)
- [Multitasking Inhibits Semantic Drift](https://mlsanity.com/paper/2104.07219/) (2021)

## Abstract (arXiv)

We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language. Our starting point is a language model that has been trained on generic, not task-specific language data. We then place this model in a multi-agent self-play environment that generates task-specific rewards used to adapt or modulate the model, turning it into a task-conditional language model. We introduce a new way for combining the two types of learning based on the idea of reranking language model samples, and show that this method outperforms others in communicating with humans in a visual referential communication task. Finally, we present a taxonomy of different types of language drift that can occur alongside a set of measures to detect them.