CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
- URL: http://arxiv.org/abs/2605.09079v1
- Date: Sat, 09 May 2026 17:39:26 GMT
- Title: CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
- Abstract summary: CauSim is a framework that turns causal reasoning from a scarce-label problem into a scalable supervised one.<n>CauSim operates across representations by formalizing non-executable causal knowledge into code, enabling data augmentation, and translating executable SCMs into natural language.
- Score: 50.047742814033654
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: causal systems are complex and often expressed in non-executable forms, while ground-truth answers to causal queries are inherently scarce. We introduce CauSim, a framework that turns causal reasoning from a scarce-label problem into a scalable supervised one. CauSim constructs increasingly complex causal simulators: executable structural causal models (SCMs), incrementally built by LLMs, that scale to globally complex systems while maintaining verifiable answers to causal queries. CauSim operates across representations by formalizing non-executable causal knowledge into code, enabling data augmentation, and translating executable SCMs into natural language, enabling supervision in previously difficult-to-supervise representations. We structure our research into two parts: (1) how to construct increasingly complex causal simulators, and (2) a systematic study of what CauSim enables, demonstrating generalization across representations, consistent gains from curriculum scaling and data volume, LLM self-improvement through self-generated simulators, and data augmentation via formalization of existing domain knowledge.
Related papers
- Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners [3.831016688248884]
Large Language Models (LLMs) achieve increasingly sophisticated performance on complex reasoning tasks.<n>Characterizing emergent reasoning is vital for long-term interpretability and safety.<n>We use a custom variant of Genetic Pareto (GEPA) to systematically optimize prompts for scientific reasoning tasks.
arXiv Detail & Related papers (2026-03-30T05:01:07Z) - CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge [14.367146529900609]
Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning.<n>We propose textbfCAusal textbfMAthematician (textbfCAMA), a two-stage causal framework that equips LLMs with explicit, reusable mathematical structure.
arXiv Detail & Related papers (2025-08-04T16:39:24Z) - Computational Thinking Reasoning in Large Language Models [69.28428524878885]
Computational Thinking Model (CTM) is a novel framework that incorporates computational thinking paradigms into large language models (LLMs)<n>Live code execution is seamlessly integrated into the reasoning process, allowing CTM to think by computing.<n>CTM outperforms conventional reasoning models and tool-augmented baselines in terms of accuracy, interpretability, and generalizability.
arXiv Detail & Related papers (2025-06-03T09:11:15Z) - Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds [9.153187514369849]
Causal world models can answer counterfactual questions about an environment of interest.<n>It requires understanding the underlying causes behind chains of events and conducting causal inference for unseen distributions.<n>We show that our approach can extract causal knowledge while reducing inference costs and spurious correlations.
arXiv Detail & Related papers (2025-05-20T14:14:05Z) - Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
arXiv Detail & Related papers (2024-10-31T12:48:58Z) - Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
We propose a framework that integrates causal representation learning with large language models.
This framework learns a causal world model, with causal variables linked to natural language expressions.
We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
arXiv Detail & Related papers (2024-10-25T18:36:37Z) - Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning [89.89857766491475]
We propose a curriculum-based logical-aware instruction tuning framework, named LACT.<n>Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition.<n> Experiments across widely used datasets demonstrate that LACT has substantial improvements(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.
arXiv Detail & Related papers (2024-05-02T18:12:08Z) - CausalCity: Complex Simulations with Agency for Causal Discovery and
Reasoning [68.74447489372037]
We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning.
A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios.
We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
arXiv Detail & Related papers (2021-06-25T00:21:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.