mlsanityData to 14 Oct 2026

Trust-Based Social Learning for Communication (TSLEC) Protocol Evolution in Multi-Agent Reinforcement Learning

arXiv 2511.19562 ↗First posted 24 Nov 2025cs.MA cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Emergent communication in multi-agent systems typically occurs through independent learning, resulting in slow convergence and potentially suboptimal protocols. We introduce TSLEC (Trust-Based Social Learning with Emergent Communication), a framework where agents explicitly teach successful strategies to peers, with knowledge transfer modulated by learned trust relationships. Through experiments with 100 episodes across 30 random seeds, we demonstrate that trust-based social learning reduces episodes-to-convergence by 23.9% (p < 0.001, Cohen's d = 1.98) compared to independent emergence, while producing compositional protocols (C = 0.38) that remain robust under dynamic objectives (Phi > 0.867 decoding accuracy). Trust scores strongly correlate with teaching quality (r = 0.743, p < 0.001), enabling effective knowledge filtering. Our results establish that explicit social learning fundamentally accelerates emergent communication in multi-agent coordination.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 15 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

8 of 15 references.

References · 8

  1. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  2. 2016Learning Multiagent Communication with Backpropagationcited by 366
  3. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  4. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 209
  5. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
  6. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
  7. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  8. 2018Learning to Teach in Cooperative Multiagent Reinforcement Learningcited by 45

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fully Independent Communication in Multi-Agent Reinforcement Learning
  2. 2025Learning Robust Social Strategies with Large Language Models
  3. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  4. 2024Multi-agent reinforcement learning in the all-or-nothing public goods game on networks ↗
  5. 2020Emergent Social Learning via Multi-agent Reinforcement Learning
  6. 2026Emergence of cooperation: A reputation-modulated reinforcement learning
  7. 2026Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
  8. 2025Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties