$How^{2}$: How to learn from procedural How-to questions

• URL: http://arxiv.org/abs/2510.11144v1
• Date: Mon, 13 Oct 2025 08:35:20 GMT
• Title: $How^{2}$: How to learn from procedural How-to questions
• Authors: Gautier Dagan, Frank Keller, Alex Lascarides,
• Abstract summary: 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.<n>We evaluate our approach in Plancraft, a Minecraft crafting environment, where agents must complete an assembly task by manipulating inventory items.
• Score: 17.933868218091856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $How^{2}$, 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. $How^{2}$ offers a way for LLM-based agents to improve their planning capabilities over time by asking questions in interactive environments.

Related papers

• Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization [56.674356045200696]
  We propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for cumbersome note systems or prior high-quality demonstration data.<n>Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights.<n>We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets.
  arXiv  Detail & Related papers  (2025-02-03T17:45:46Z)
• Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering [6.6897007888321465]
  We propose a voting framework for knowledge-based Visual Question Answering.<n>We design three agents that simulate different levels of staff in a team, and assign the available tools according to the levels.<n>Experiments on OK-VQA and A-OKVQA show that our approach outperforms other baselines by 2.2 and 1.0, respectively.
  arXiv  Detail & Related papers  (2024-12-24T11:24:56Z)
• KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents [52.34892973785117]
  Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges.<n>This inadequacy primarily stems from the lack of built-in action knowledge in language agents.<n>We introduce KnowAgent, a novel approach designed to enhance the planning capabilities of LLMs by incorporating explicit action knowledge.
  arXiv  Detail & Related papers  (2024-03-05T16:39:12Z)
• AVIS: Autonomous Visual Information Seeking with Large Language Model Agent [123.75169211547149]
  We propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools. AVIS achieves state-of-the-art results on knowledge-intensive visual question answering benchmarks such as Infoseek and OK-VQA.
  arXiv  Detail & Related papers  (2023-06-13T20:50:22Z)
• Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach [31.6589518077397]
  Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. We propose When2Ask, a reinforcement learning based approach that learns when it is necessary to query LLMs for high-level instructions.
  arXiv  Detail & Related papers  (2023-06-06T11:49:09Z)
• Successive Prompting for Decomposing Complex Questions [50.00659445976735]
  Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting. We introduce Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Our best model (with successive prompting) achieves an improvement of 5% absolute F1 on a few-shot version of the DROP dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:03:38Z)
• Ask Before You Act: Generalising to Novel Environments by Asking Questions [0.0]
  We investigate the ability of an RL agent to learn to ask natural language questions as a tool to understand its environment. We do this by endowing this agent with the ability of asking "yes-no" questions to an all-knowing Oracle. We observe a significant increase in generalisation performance compared to a baseline agent unable to ask questions.
  arXiv  Detail & Related papers  (2022-09-10T13:17:21Z)
• Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language [121.56329458876655]
  We introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. We propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge.
  arXiv  Detail & Related papers  (2022-05-12T14:20:31Z)
• Learning When and What to Ask: a Hierarchical Reinforcement Learning Framework [17.017688226277834]
  We formulate a hierarchical reinforcement learning framework for learning to decide when to request additional information from humans. Results on a simulated human-assisted navigation problem demonstrate the effectiveness of our framework.
  arXiv  Detail & Related papers  (2021-10-14T01:30:36Z)
• Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning [56.771557756836906]
  We present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases.
  arXiv  Detail & Related papers  (2020-10-29T18:28:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.