# Causal Reflection with Language Models

arXiv: https://arxiv.org/abs/2508.04495 · HTML: https://mlsanity.com/paper/2508.04495/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 12 of 12)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Causal Influence Detection for Improving Efficiency in Reinforcement Learning](https://mlsanity.com/paper/2106.03443/) (2021)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [Large Language Models for Causal Discovery: Current Landscape and Future Directions](https://mlsanity.com/paper/2402.11068/) (2024)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [Cause and Effect: Can Large Language Models Truly Understand Causality?](https://mlsanity.com/paper/2402.18139/) (2024)
- [Language Agents Meet Causality -- Bridging LLMs and Causal World Models](https://mlsanity.com/paper/2410.19923/) (2024)
- [Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains](https://mlsanity.com/paper/2506.17718/) (2025)
- [Adversarial Causal Tuning for Realistic Time-series Generation](https://mlsanity.com/paper/2506.02084/) (2025)
- [Inferring the time-varying coupling of dynamical systems with temporal convolutional autoencoders](https://mlsanity.com/paper/2406.03212/) (2024)
- [A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference](https://mlsanity.com/paper/2503.17803/) (2025)

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

- [AbideGym: Turning Static RL Worlds into Adaptive Challenges](https://mlsanity.com/paper/2509.21234/) (2025)

## Abstract (arXiv)

While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, traditional Reinforcement Learning agents also lack causal understanding, optimizing for rewards without modeling why actions lead to outcomes. We introduce Causal Reflection, a framework that explicitly models causality as a dynamic function over state, action, time, and perturbation, enabling agents to reason about delayed and nonlinear effects. Additionally, we define a formal Reflect mechanism that identifies mismatches between predicted and observed outcomes and generates causal hypotheses to revise the agent's internal model. In this architecture, LLMs serve not as black-box reasoners, but as structured inference engines translating formal causal outputs into natural language explanations and counterfactuals. Our framework lays the theoretical groundwork for Causal Reflective agents that can adapt, self-correct, and communicate causal understanding in evolving environments.