mlsanityData to 14 Oct 2026

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess

arXiv 2507.00726 ↗First posted 1 Jul 2025cs.AI cs.LGcited by 9

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

While reinforcement learning (RL) for large language models (LLMs) has shown promise in mathematical reasoning, strategic reasoning for LLMs using RL remains largely unexplored. We investigate whether LLMs can develop strategic reasoning capabilities through RL in chess. To this end, we leverage a chess-pretrained action-value network to provide dense reward on the LLM's output move quality, which can be seen as a form of knowledge distillation. Our experiments show that our distillation-based dense rewards often outperform sparse binary rewards. However, surprisingly, all models plateau far below expert levels. We provide SFT and RL ablations on chess reasoning training and find evidence that this limitation stems from a deficit in the pretrained models' internal understanding of chess-a deficit which RL alone may not be able to fully overcome. The code is available at https://github.com/krafton-ai/Chess-R1.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 23 of its 30 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

23 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Explore the Reasoning Capability of LLMs in the Chess Testbed11 Nov
  2. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models1 Apr

Other references · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  7. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  8. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  9. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  10. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  11. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  12. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 513
9 more
  1. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 344
  2. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Examplecited by 295
  3. 2025Spurious Rewards: Rethinking Training Signals in RLVRcited by 209
  4. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  5. 2025Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretrainingcited by 129
  6. 2025Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learningcited by 40
  7. 2025Learning to Reason for Long-Form Story Generationcited by 34
  8. 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Gamescited by 31
  9. 2025Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?cited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2026Grounded Chess Reasoning in Language Models via Master Distillationcited by 5
  2. 2025ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Modelscited by 3
  3. 2026Learning Stateful Predictive Knowledge From Experiencecited by 2
  4. 2026Mixture of Masters: Sparse Chess Language Models with Player Routingcited by 1
  5. 2026VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Studycited by 1
  6. 2026Playing with Words, Improving with Rewards: Training Language Models for Creative Associationcited by 0
  7. 2026The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoningcited by 0
  8. 2026Benchmarking Prompt Optimization of Large Language Models With Chesscited by 0
  9. 2026Representation-Aligned Auxiliary Supervision for Language Model Adaptationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Understanding Reasoning from Pretraining to Post-Training
  2. 2026How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
  3. 2025LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
  4. 2025Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning
  5. 2026What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
  6. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  7. 2024On the Modeling Capabilities of Large Language Models for Sequential Decision Making
  8. 2025A Survey of Reinforcement Learning for Large Reasoning Models