# Explaining Agent Behavior with Large Language Models

*Source* · `src-zhang-2023-explaining-agent-behavior` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell |
| venue | arXiv |
| date | 2023-09-19 |
| url | https://arxiv.org/abs/2309.10346 |
| arxiv | 2309.10346 |
| accessed | 2026-10-24 |

## Notes

Learns a compact behavior representation from observed states and actions without model internals, then prompts an LLM to explain; little hallucination; rated about as helpful as a human domain expert; supports follow-up clarification and what-if questions.

## Backlinks (computed)

**cited by:** [LLM explanation of simulation state](../technique/llm-explanation-of-state.md)

## Citation

Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell (2023-09-19). *Explaining Agent Behavior with Large Language Models*. arXiv https://arxiv.org/abs/2309.10346

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.