# Group Causal Policy Optimization for Post-Training Large Language Models

arXiv: https://arxiv.org/abs/2508.05428 · HTML: https://mlsanity.com/paper/2508.05428/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2025.

## Built on by (most cited first, 4 of 4)

- [On the Plasticity and Stability for Post-Training Large Language Models](https://mlsanity.com/paper/2602.06453/) (2026)
- [Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2602.06475/) (2026)
- [Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design](https://mlsanity.com/paper/2603.13312/) (2026)
- [Pareto-Guided Optimal Transport for Multi-Reward Alignment](https://mlsanity.com/paper/2605.13155/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands out for its efficiency, leveraging groupwise relative rewards while avoiding costly value function learning. However, GRPO treats candidate responses as independent, overlooking semantic interactions such as complementarity and contradiction. To address this challenge, we first introduce a Structural Causal Model (SCM) that reveals hidden dependencies among candidate responses induced by conditioning on a final integrated output forming a collider structure. Then, our causal analysis leads to two insights: (1) projecting responses onto a causally informed subspace improves prediction quality, and (2) this projection yields a better baseline than query only conditioning. Building on these insights, we propose Group Causal Policy Optimization (GCPO), which integrates causal structure into optimization through two key components: a causally informed reward adjustment and a novel KL regularization term that aligns the policy with a causally projected reference distribution. Comprehensive experimental evaluations demonstrate that GCPO consistently surpasses existing methods, including GRPO across multiple reasoning benchmarks.