ACL Findings2026
GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement for High-Density Reasoning
Zuchao Li, Qiwei Li, Yao Yao, Hai Zhao, Lefei Zhang, Bo Du
Abstract
Chain-of-Thought (CoT) reasoning, while effective, suffers from an inherent mechanism flaw: linearity induces overthinking. Constrained by sequential generation, models often produce redundant narration and circular self-corrections to maintain logical context. We propose GoT-R1, a framework that fundamentally mitigates this by replacing verbose linear trajectories with high-density reasoning graphs. Unlike CoT, GoT-R1 decouples logic from narration, modeling deliberation as a structured topology of atomic units. We internalize this inductive bias via a two-stage regimen: synthesizing structural data to distill logical skeletons, followed by Group Relative Policy Optimization (GRPO) to explicitly reinforce topological integrity. Extensive evaluations across mathematical reasoning and instruction following demonstrate that GoT-R1 consistently outperforms state-of-the-art baselines. Crucially, it achieves these gains with significantly reduced token overhead, demonstrating that structured reasoning density offers a more robust and parsimonious alternative to the recursive verbosity of standard CoT. The GoT-R1 models are open-sourced on Hugging Face at: https://huggingface.co/ collections/MYTH-Lab/got-r1.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on17
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
- TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
- STaR: Bootstrapping Reasoning With ReasoningEric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. GoodmanNeurIPS 2022 · 1,126 citations
Related papers
- Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMsHongyuan Yuan, Xinran He, Run Shao, Bolei He et al.ACL Findings 2026
- RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts ReasoningYuhang Liu, Ruijie Wang, Yunlong Chu, Bing Hao et al.KDD 2026 · 1 citation
- GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language ModelsJixiao Zhang, Chunsheng ZuoEMNLP 2025 · 1 citation
- On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case StudyRiccardo Alberghi, Elizaveta Demyanenko, Luca Biggio, Luca SagliettiNeurIPS 2025 · 2 citations
- Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning ModelsJiawei Li, Yang Gao, Huashan Sun, Chong FengACL 2026
