Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems

2026-01-29

AI Summary

This work addresses the challenge of blind conformity in multi-agent systems, where agents often lack effective mechanisms to assess the reliability of their peers. To mitigate this, the authors propose the Epistemic Context Learning (ECL) framework, which explicitly integrates peer trustworthiness profiles—constructed from historical interactions—into in-context learning for the first time. By combining reinforcement learning with an auxiliary reward mechanism, ECL optimizes trust modeling, enabling agents to selectively learn from more reliable peers under uncertainty and recasting reasoning quality assessment as an estimation of historical reliability. Experimental results demonstrate that ECL, implemented with the Qwen-3-4B model, outperforms baseline models up to eight times larger in scale, achieves near-perfect accuracy in advanced configurations, and exhibits strong generalization across diverse multi-agent settings.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Online Learning & Bandits
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Individual agents in multi-agent (MA) systems often lack robustness, tending to blindly conform to misleading peers. We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability. To address this, we first formalize the learning problem of history-aware reference, introducing the historical interactions of peers as additional input, so that agents can estimate peer reliability and learn from trustworthy peers when uncertain. This shifts the task from evaluating peer reasoning quality to estimating peer reliability based on interaction history. We then develop Epistemic Context Learning (ECL): a reasoning framework that conditions predictions on explicitly-built peer profiles from history. We further optimize ECL by reinforcement learning using auxiliary rewards. Our experiments reveal that our ECL enables small models like Qwen 3-4B to outperform a history-agnostic baseline 8x its size (Qwen 3-30B) by accurately identifying reliable peers. ECL also boosts frontier models to near-perfect (100%) performance. We show that ECL generalizes well to various MA configurations and we find that trust is modeled well by LLMs, revealing a strong correlation in trust modeling accuracy and final answer quality.

Problem

• multi-agent systems
• peer reliability
• epistemic trust
• LLM robustness
• conformity bias

Innovation

• Epistemic Context Learning
• multi-agent systems
• trust modeling
• history-aware reasoning
• reinforcement learning