# CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs

arXiv: https://arxiv.org/abs/2509.00971 · HTML: https://mlsanity.com/paper/2509.00971/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs](https://mlsanity.com/paper/2505.00127/) (2025)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts](https://mlsanity.com/paper/2201.10295/) (2022)
- [Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models](https://mlsanity.com/paper/2506.04210/) (2025)
- [Let LRMs Break Free from Overthinking via Self-Braking Tuning](https://mlsanity.com/paper/2505.14604/) (2025)
- [Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.09250/) (2025)
- [Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition](https://mlsanity.com/paper/2409.19250/) (2024)
- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models](https://mlsanity.com/paper/2505.16448/) (2025)
- [Visual Question Answering in the Medical Domain](https://mlsanity.com/paper/2309.11080/) (2023)
- [Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture](https://mlsanity.com/paper/2409.13153/) (2024)
- [Neurosymbolic AI and its Taxonomy: a survey](https://mlsanity.com/paper/2305.08876/) (2023)
- [PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving](https://mlsanity.com/paper/2507.07495/) (2025)
- [A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives](https://mlsanity.com/paper/2503.18213/) (2025)
- [Transparent AI: The Case for Interpretability and Explainability](https://mlsanity.com/paper/2507.23535/) (2025)
- [The Case Against Explainability](https://mlsanity.com/paper/2305.12167/) (2023)

## Built on by (most cited first, 3 of 3)

- [What If We Allocate Test-Time Compute Adaptively?](https://mlsanity.com/paper/2602.01070/) (2026)
- [On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset](https://mlsanity.com/paper/2510.22898/) (2025)
- [Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning](https://mlsanity.com/paper/2609.00367/) (2026)

## Abstract (arXiv)

We introduce CoreThink, a state-of-the-art Reasoning Layer built upon a novel reasoning method called General Symbolics. This approach diverges from reasoning paradigms such as test-time scaling, Supervised Fine-Tuning (SFT), and Reinforcement Learning with Verifiable Rewards (RLVR). CoreThink General Symbolic Reasoner (GSR) is specifically structured around three key use cases: tool-calling, code generation, and planning, demonstrating exemplary performance across a total of seven benchmarks in their respective areas. Notably, we are achieving SOTA scores of 66.66% on Livecodebench v6, 89% on Instruction-Following Evals, and 24.4% on ARC-AGI-2. We also present an agentic coding IDE, developed using the principles of General Symbolics, which achieves a state-of-the-art accuracy of 62.3% on SWE-Bench Lite. We are able to achieve these improvements without any fine-tuning or training costs. Our Reasoning Layer is designed to provide a pure performance uplift, ensuring that a model's accuracy on reasoning tasks is never negatively impacted. We argue that incumbent methods will eventually lead to diminishing returns in LLM performance, necessitating the development of new reasoning techniques. This technical report details our approach at a high level and the availability of the CoreThink models for reasoning-intensive use cases.