# Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis

arXiv: https://arxiv.org/abs/2306.06770 · HTML: https://mlsanity.com/paper/2306.06770/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 11 Jun 2023.

## Placed in

- 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, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [TidyBot: Personalized Robot Assistance with Large Language Models](https://mlsanity.com/paper/2305.05658/) (2023)
- [Active Prompting with Chain-of-Thought for Large Language Models](https://mlsanity.com/paper/2302.12246/) (2023)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors](https://mlsanity.com/paper/2207.10761/) (2022)
- [GPT3-to-plan: Extracting plans from text using GPT-3](https://mlsanity.com/paper/2106.07131/) (2021)
- [Few-shot Subgoal Planning with Language Models](https://mlsanity.com/paper/2205.14288/) (2022)
- [Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks](https://mlsanity.com/paper/2208.09554/) (2022)
- [Improving Language Model Prompting in Support of Semi-autonomous Task Learning](https://mlsanity.com/paper/2209.07636/) (2022)

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

- [Eliciting Problem Specifications via Large Language Models](https://mlsanity.com/paper/2405.12147/) (2024)

## Abstract (arXiv)

Large language models (LLMs) offer significant promise as a knowledge source for task learning. Prompt engineering has been shown to be effective for eliciting knowledge from an LLM, but alone it is insufficient for acquiring relevant, situationally grounded knowledge for an embodied agent learning novel tasks. We describe a cognitive-agent approach, STARS, that extends and complements prompt engineering, mitigating its limitations and thus enabling an agent to acquire new task knowledge matched to its native language capabilities, embodiment, environment, and user preferences. The STARS approach is to increase the response space of LLMs and deploy general strategies, embedded within the autonomous agent, to evaluate, repair, and select among candidate responses produced by the LLM. We describe the approach and experiments that show how an agent, by retrieving and evaluating a breadth of responses from the LLM, can achieve 77-94% task completion in one-shot learning without user oversight. The approach achieves 100% task completion when human oversight (such as an indication of preference) is provided. Further, the type of oversight largely shifts from explicit, natural language instruction to simple confirmation/discomfirmation of high-quality responses that have been vetted by the agent before presentation to a user.