# The Curious Language Model: Strategic Test-Time Information Acquisition

arXiv: https://arxiv.org/abs/2506.09173 · HTML: https://mlsanity.com/paper/2506.09173/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://mlsanity.com/paper/2309.17452/) (2023)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents](https://mlsanity.com/paper/2408.14033/) (2024)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?](https://mlsanity.com/paper/2503.22674/) (2025)
- [BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments](https://mlsanity.com/paper/2405.17631/) (2024)
- [ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change](https://mlsanity.com/paper/2401.09646/) (2024)
- [Ask the Right Questions: Active Question Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1705.07830/) (2017)
- [Learning to Ask: When LLM Agents Meet Unclear Instruction](https://mlsanity.com/paper/2409.00557/) (2024)
- [Validating Large Language Models with ReLM](https://mlsanity.com/paper/2211.15458/) (2022)
- [Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning](https://mlsanity.com/paper/2402.06025/) (2024)
- [Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain](https://mlsanity.com/paper/2406.17453/) (2024)
- [LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error](https://mlsanity.com/paper/2403.04746/) (2024)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [A Survey on Active Feature Acquisition Strategies](https://mlsanity.com/paper/2502.11067/) (2025)

## Built on by (most cited first, 5 of 5)

- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [Planning to Explore: Curiosity-Driven Planning for LLM Test Generation](https://mlsanity.com/paper/2604.05159/) (2026)
- [Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients](https://mlsanity.com/paper/2605.05511/) (2026)
- [CA-BED: Conversation-Aware Bayesian Experimental Design](https://mlsanity.com/paper/2606.01182/) (2026)
- [Wide Learning: Learning to Reach Evidence](https://mlsanity.com/paper/2608.29608/) (2026)

## Abstract (arXiv)

Decision-makers often possess insufficient information to render a confident decision. In these cases, the decision-maker can often undertake actions to acquire the necessary information about the problem at hand, e.g., by consulting knowledgeable authorities or by conducting experiments. Importantly, different levers of information acquisition come with different costs, posing the challenge of selecting the actions that are both informative and cost-effective. In this work, we propose CuriosiTree, a heuristic-based, test-time policy for zero-shot information acquisition in large language models (LLMs). CuriosiTree employs a greedy tree search to estimate the expected information gain of each action and strategically chooses actions based on a balance of anticipated information gain and associated cost. Empirical validation in a clinical diagnosis simulation shows that CuriosiTree enables cost-effective integration of heterogenous sources of information, and outperforms baseline action selection strategies in selecting action sequences that enable accurate diagnosis.