mlsanityData to 7 Oct 2026

Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators

arXiv 2605.07600 ↗First posted 8 May 2026cs.LG cs.AI cs.CLcited by 0

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify which concepts causally contribute to a correct answer, as the observed association may be spurious, driven by confounders such as problem difficulty. We propose CIKA (Causal Intervention for Knowledge Activation), a framework that uses the LLM itself as an interventional simulator: a prompt sets the concept state to ``mastered'' and the correctness change estimates the causal effect. We formalize this quantity as an Interventional Capability Probe (ICP), which diagnoses whether the LLM can use a given concept -- distinct from merely possessing knowledge. Because the intervention exogenously sets the concept state independently of problem difficulty, ICP separates confounding that observational methods cannot. On 67 screened problems, the ICP of the top-ranked concept (+0.219) is significantly larger than that of the negative control (+0.039; paired t-test, p < 10-6, Cohen's d = 0.86), confirming that the probe discriminates causally relevant concepts from irrelevant ones. Analysis of 601 Omni-MATH problems further shows that solved problems have 6.1× higher ATE than unsolved ones (0.338 vs. 0.055), confirming that ICP is predictive of problem-solving success. With a 7B-parameter LLM whose weights are entirely frozen, CIKA achieves 69.7% on the contamination-free Omni-MATH-Rule benchmark and 64.0% overall, compared to 60.5% for o1-mini, and 97.2% on GSM8K, 46--50% on AIME 2024--2026, and 46.2% on MathArena. The Causal Knowledge Activation component contributes 33.8% of correct answers on problems where the base model alone fails, demonstrating that the LLM already possessed but had not activated the requisite knowledge.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 13 of its 37 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

13 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Evaluating Interventional Reasoning Capabilities of Large Language Models8 Apr

Other references · 12

  1. 2023Let's Verify Step by Stepcited by 3,598
  2. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  3. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  4. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 165
  5. 2024LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoningcited by 90
  6. 2024Causality for Large Language Modelscited by 24
  7. 2026PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoningcited by 17
  8. 2025CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Modelcited by 9
  9. 2025Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTScited by 4
  10. 2025The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentationcited by 3
  11. 2025Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustmentcited by 1
  12. 2025Extending Lifetime of Embedded Systems by WebAssembly-based Functional Extensions Including Driverscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
  2. 2024Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
  3. 2023Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning
  4. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery
  5. 2025KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?
  6. 2026Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification
  7. 2025Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks
  8. 2026Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction