mlsanityData to 7 Oct 2026

Causal Reflection with Language Models

arXiv 2508.04495 ↗First posted 6 Aug 2025cs.LG cs.CLcited by 1

On the map: LLM reasoning → Causal reasoning in LLMs

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.

Key facts. Cited by 1 paper in the map (data through 7 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.

Builds on

12 of 19 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?26 Jun
  2. 2025A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference22 Mar
  3. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality28 Apr

Other references · 9

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  3. 2024Large Language Models for Causal Discovery: Current Landscape and Future Directionscited by 25
  4. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
  5. 2023Causal Reinforcement Learning: A Surveycited by 22
  6. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Modelscited by 8
  7. 2025Learning Time-Aware Causal Representation for Model Generalization in Evolving Domainscited by 5
  8. 2025Adversarial Causal Tuning for Realistic Time-series Generationcited by 3
  9. 2024Inferring the time-varying coupling of dynamical systems with temporal convolutional autoencoderscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025AbideGym: Turning Static RL Worlds into Adaptive Challengescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
  2. 2025Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
  3. 2026An Introduction to Causal Reinforcement Learning
  4. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Models
  5. 2026CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
  6. 2026Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
  7. 2023Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
  8. 2024Failure Modes of LLMs for Causal Reasoning on Narratives