CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning Article Swipe

MAKE IMPACT

Minh Hoang Nguyen , Van Dai Do , Dung Huu Nguyen , Thin Nguyen , Hung Lê · YOU? · · 2025 · Open Access ·

Large language model (LLM) agents-especially smaller, open-source models-often produce causally invalid or incoherent actions in collaborative tasks due to their reliance on surface-level correlations rather than grounded causal reasoning. This limitation undermines their performance in terms of coordination and planning in dynamic environments. We address this challenge with CausalPlan, a two-phase framework that integrates explicit structural causal reasoning into the LLM planning process. At the core of CausalPlan is the Structural Causal Action (SCA) model, which learns a causal graph from agent trajectories to capture how prior actions and current environment states influence future decisions. This structure is then used to guide action selection by assigning causal scores to LLM-generated proposals, reweighting them accordingly, or falling back to causally grounded alternatives when needed. By embedding this causal knowledge directly into the decision loop, CausalPlan constrains planning to intervention-consistent behaviours without requiring fine-tuning of the LLM itself. We evaluate CausalPlan on the Overcooked-AI benchmark across five multi-agent coordination tasks and four LLMs of varying sizes: Gemma-7B, Llama-8B, Qwen-14B, and Llama-70B. Experimental results show that CausalPlan consistently reduces invalid actions and improves collaboration in both AI-AI and human-AI settings, outperforming strong reinforcement learning baselines. Our findings highlight the value of causality-driven planning for deploying efficient, interpretable, and generalisable multi-agent LLM systems.

Type

article

Language

en

Landing Page

http://arxiv.org/abs/2508.13721

PDF

https://arxiv.org/pdf/2508.13721

OA Status

green

OpenAlex ID

https://openalex.org/W4414536845

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414536845

Canonical identifier for this work in OpenAlex

Title

CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning

Work title

Type

article

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-08-19

Full publication date if available

Authors

Minh Hoang Nguyen, Van Dai Do, Dung Huu Nguyen, Thin Nguyen, Hung Lê

List of authors in order

Landing page

https://arxiv.org/abs/2508.13721

Publisher landing page

PDF URL

https://arxiv.org/pdf/2508.13721

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2508.13721

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload