# How2: How to learn from procedural How-to questions

arXiv: https://arxiv.org/abs/2510.11144 · HTML: https://mlsanity.com/paper/2510.11144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents](https://mlsanity.com/paper/2402.03610/) (2024)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Learning to Ask: When LLM Agents Meet Unclear Instruction](https://mlsanity.com/paper/2409.00557/) (2024)
- [Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge](https://mlsanity.com/paper/2104.06828/) (2021)
- [MoT: Memory-of-Thought Enables ChatGPT to Self-Improve](https://mlsanity.com/paper/2305.05181/) (2023)
- [Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions](https://mlsanity.com/paper/2402.06509/) (2024)
- [Open-domain clarification question generation without question examples](https://mlsanity.com/paper/2110.09779/) (2021)
- [Plancraft: an evaluation dataset for planning with LLM agents](https://mlsanity.com/paper/2412.21033/) (2024)
- [Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language](https://mlsanity.com/paper/2205.06111/) (2022)
- [Interactive Question Clarification in Dialogue via Reinforcement Learning](https://mlsanity.com/paper/2012.09411/) (2020)
- [Graph Guided Question Answer Generation for Procedural Question-Answering](https://mlsanity.com/paper/2401.13594/) (2024)

## Built on by (most cited first, 1 of 1)

- [Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication](https://mlsanity.com/paper/2602.02843/) (2026)

## Abstract (arXiv)

An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?" range from executable actions to high-level descriptions of X's sub-goals, makes them challenging for AI agents to ask, and for AI experts to answer, in ways that support efficient planning. We introduce How2, a memory agent framework that enables agents to ask how-to questions, store the answers, and reuse them for lifelong learning in interactive environments. We evaluate our approach in Plancraft, a Minecraft crafting environment, where agents must complete an assembly task by manipulating inventory items. Using teacher models that answer at varying levels of abstraction, from executable action sequences to high-level subgoal descriptions, we show that lifelong learning agents benefit most from answers that are abstracted and decoupled from the current state. How2 offers a way for LLM-based agents to improve their planning capabilities over time by asking questions in interactive environments.