# Active Inference as Context Acquisition for AI Agents

arXiv: https://arxiv.org/abs/2608.19202 · HTML: https://mlsanity.com/paper/2608.19202/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 29 of 29)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Learning to Optimize via Information-Directed Sampling](https://mlsanity.com/paper/1403.5556/) (2014)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [On the Relationship Between Active Inference and Control as Inference](https://mlsanity.com/paper/2006.12964/) (2020)
- [Learning to Ask: When LLM Agents Meet Unclear Instruction](https://mlsanity.com/paper/2409.00557/) (2024)
- [Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF](https://mlsanity.com/paper/2402.06886/) (2024)
- [Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models](https://mlsanity.com/paper/2402.03271/) (2024)
- [Active Preference Inference using Language Models and Probabilistic Reasoning](https://mlsanity.com/paper/2312.12009/) (2023)
- [Fine-Tuning Large Language Models with User-Level Differential Privacy](https://mlsanity.com/paper/2407.07737/) (2024)
- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [Active Task Disambiguation with LLMs](https://mlsanity.com/paper/2502.04485/) (2025)
- [A Method for Stopping Active Learning Based on Stabilizing Predictions and the Need for User-Adjustable Stopping](https://mlsanity.com/paper/1409.5165/) (2014)
- [Contextual Bilevel Reinforcement Learning for Incentive Alignment](https://mlsanity.com/paper/2406.01575/) (2024)
- [Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control](https://mlsanity.com/paper/2103.06859/) (2021)
- [Applications of the Free Energy Principle to Machine Learning and Neuroscience](https://mlsanity.com/paper/2107.00140/) (2021)
- [Lifting the Veil on Composition, Risks, and Mitigations of the Large Language Model Supply Chain](https://mlsanity.com/paper/2410.21218/) (2024)
- [Bi-Level Policy Optimization with Nystr"om Hypergradients](https://mlsanity.com/paper/2505.11714/) (2025)
- [A Meta-Bayesian Model of Intentional Visual Search](https://mlsanity.com/paper/2006.03531/) (2020)

## Abstract (arXiv)

Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.