All papers — page 6
- Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
arxiv:2606.29150· 2026-06-28 · text available - For SALE: State-Action Representation Learning for Deep Reinforcement Learning
arxiv:2306.02451· 2023-06-04 · text available - From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
arxiv:2509.25123· 2025-09-29 · text available - From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
arxiv:2405.14838· 2024-05-23 · text available - From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
arxiv:2605.22074· 2026-05-21 · text available - From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
arxiv:2505.17117· 2025-05-21 · text available - Fully parallel optical matrix-matrix multiplication
arxiv:2309.10232· 2023-09-19 · text available - Generative Recursive Reasoning
arxiv:2605.19376· 2026-05-19 · text available - GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
arxiv:2507.19457· 2025-07-25 · text available - GLU Variants Improve Transformer
arxiv:2002.05202· 2020-02-12 · text available - Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
arxiv:2602.18037· 2026-02-20 · text available - Grokfast: Accelerated Grokking by Amplifying Slow Gradients
arxiv:2405.20233· 2024-05-30 · text available - Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
arxiv:2405.15071· 2024-05-23 · text available - Grokking Group Multiplication with Cosets
openreview:hcQfTsVnBo· 2023-12-11 · text available - Group Sequence Policy Optimization
arxiv:2507.18071· 2025-07-24 · text available - Group-in-Group Policy Optimization for LLM Agent Training
arxiv:2505.10978· 2025-05-16 · text available - GRPO++: Tricks for Making RL Actually Work (Cameron Wolfe)
url:cameronrwolfe.substack.com/p/grpo-tricks· 2026-01-05 · metadata only - GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
arxiv:2604.20659· 2026-04-22 · text available - gzip Predicts Data-dependent Scaling Laws
arxiv:2405.16684· 2024-05-26 · text available - Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
arxiv:2410.04444· 2024-10-06 · text available - Harness Engineering (OpenAI)
url:openai.com/index/harness-engineering· 2026-08-25 · metadata only - HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
arxiv:2609.01437· 2026-09-01 · text available - Harnesses for models (Lilian Weng, 2026)
url:lilianweng.github.io/posts/2026-07-04-harness· 2026-07-04 · metadata only - Harnessing Agentic Evolution
arxiv:2605.13821· 2026-05-13 · text available