mlsanityData to 7 Oct 2026

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

arXiv 2005.07064 ↗First posted 14 May 2020cs.CL cs.AI cs.LGcited by 65

Not on the map. Why?

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.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 14; 2024: 12; 2025: 10; 2026: 5.

65 papers.

Sort:

By area:

  1. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  2. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  3. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  4. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  5. 2025Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetycited by 222
  6. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  7. 2024WARM: On the Benefits of Weight Averaged Reward Modelscited by 145
  8. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  9. 2024BOND: Aligning LLMs with Best-of-N Distillationcited by 73
  10. 2021Modeling Strong and Human-Like Gameplay with KL-Regularized Searchcited by 50
  11. 2024WARP: On the Benefits of Weight Averaged Rewarded Policiescited by 42
  12. 2021Emergent Communication of Generalizationscited by 41
38 more
  1. 2023Language Model Alignment with Elastic Resetcited by 34
  2. 2024LLM Harmony: Multi-Agent Communication for Problem Solvingcited by 34
  3. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  4. 2024Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learningcited by 20
  5. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  6. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  7. 2023Computational Language Acquisition with Theory of Mindcited by 15
  8. 2024Diffusion Guided Language Modelingcited by 15
  9. 2022Learning to Mediate Disparities Towards Pragmatic Communicationcited by 14
  10. 2024LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Modelscited by 14
  11. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  12. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  13. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  14. 2025Once Upon a Time: Interactive Learning for Storytelling with Small Language Modelscited by 11
  15. 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
  16. 2021Calibrate your listeners! Robust communication-based training for pragmatic speakerscited by 9
  17. 2025Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interactioncited by 9
  18. 2021Multitasking Inhibits Semantic Driftcited by 8
  19. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  20. 2022Emergent Quantized Communicationcited by 7
  21. 2022Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Modelscited by 7
  22. 2023Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mindcited by 7
  23. 2025Success and Cost Elicit Convention Formation for Efficient Communicationcited by 7
  24. 2022Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibriacited by 6
  25. 2022Intra-agent speech permits zero-shot task acquisitioncited by 5
  26. 2023Evaluating Pragmatic Abilities of Image Captioners on A3DScited by 5
  27. 2023Generating Pragmatic Examples to Train Neural Program Synthesizerscited by 5
  28. 2025EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulationcited by 5
  29. 2021Statistical discrimination in learning agentscited by 4
  30. 2022Learning to translate by learning to communicatecited by 4
  31. 2023Pragmatic Inference with a CLIP Listener for Contrastive Captioningcited by 4
  32. 2025A Distributional Perspective on Word Learning in Neural Language Modelscited by 4
  33. 2025Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Modelscited by 4
  34. 2022Know your audience: specializing grounded language models with listener subtractioncited by 3
  35. 2023ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formationcited by 3
  36. 2024Optimal Decision Making Through Scenario Simulations Using Large Language Modelscited by 3
  37. 2021Learning Natural Language Generation from Scratchcited by 2
  38. 2023Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minimacited by 2

50 most cited of 65 All 65 (JSON)