# The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents

arXiv: https://arxiv.org/abs/2512.20884 · HTML: https://mlsanity.com/paper/2512.20884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

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

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles](https://mlsanity.com/paper/2401.00243/) (2023)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [Improving Uncertainty Sampling with Bell Curve Weight Function](https://mlsanity.com/paper/2403.01352/) (2024)
- [Leveraging Approximate Caching for Faster Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.05530/) (2025)

## Abstract (arXiv)

Autonomous agents powered by LLMs and Retrieval-Augmented Generation (RAG) are proficient consumers of digital content but remain unidirectional, a limitation we term epistemic asymmetry. This isolation leads to redundant reasoning and stagnates collective intelligence. Current self-reflection frameworks remain largely heuristic and private, lacking a probabilistic foundation to quantify certainty or justify external interaction.To bridge this gap, we propose a formal probabilistic framework that provides agents with a non-altruistic motive for bidirectional knowledge exchange. We model an agent's belief in a proposition using a Beta-Bernoulli distribution with a forgetting factor (γ). This allows us to isolate epistemic uncertainty as the variance of belief, establishing a dual drive for interaction: A homeostatic motive: The need to maintain certainty against the temporal decay introduced by γ. An optimal learning strategy: Targeting points of maximum ambiguity (mathbbE[θ]=0.5) to maximize information gain. Under this framework, public contribution is reframed as optimal active learning: sharing solutions to elicit feedback is the most efficient method for an agent to reduce its own uncertainty. To ensure scalability, we introduce epistemic caching, which leverages the forgetting factor to dynamically prioritize resources for the active head of non-stationary knowledge distributions. Finally, we demonstrate how these accumulated belief states serve as verifiable reward signals for Reinforcement Learning from Human Feedback (RLHF) and high-quality data filters for Supervised Fine-Tuning (SFT). Simulation results validate that this uncertainty-driven strategy significantly outperforms random baselines in heterogeneous (Zipfian) environments, maintaining high adaptability to concept drift.