mlsanityData to 7 Oct 2026

Latent Poincar'e Shaping for Agentic Reinforcement Learning

arXiv 2602.09375 ↗First posted 10 Feb 2026cs.LGcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincar'e latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and growing outward from the origin toward the boundary of the Poincar'e ball, where negative curvature provides exponentially increasing capacity with radius. Using hyperbolic geodesic distance to rule-verified correctness, we define a node potential and assign dense process rewards by potential differences. We further attach a lightweight value head on the same shared latent space, enabling self-guided test-time scaling with almost no additional overhead. On MATH-500, LaPha improves Qwen2.5-Math-1.5B from 66.0% to 88.2%. With value-head-guided search, LaPha-1.5B reaches 56.7% accuracy on AIME'24, and LaPha-7B further achieves 60.0% on AIME'24 and 53.3% on AIME'25.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 38 references that are in the map. First posted on arXiv 10 Feb 2026.

Builds on

24 of 38 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  8. 2019Root Mean Square Layer Normalizationcited by 1,425
  9. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  10. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  12. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
12 more
  1. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  2. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  3. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 540
  4. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 402
  5. 2018Hyperbolic Neural Networkscited by 393
  6. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  7. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  8. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  9. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 276
  10. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 238
  11. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 182
  12. 2025Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubtcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ARLArena: A Unified Framework for Stable Agentic Reinforcement Learningcited by 11

Similar, not cited

Close in wording, no citation either way

  1. 2025Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
  2. 2026Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
  3. 2026Agent-G2: Gaussian Guidance for Agentic Reinforcement Learning
  4. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
  5. 2026AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
  6. 2026Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
  7. 2026AgentV-RL: Scaling Reward Modeling with Agentic Verifier
  8. 2025Towards Agentic Self-Learning LLMs in Search Environment