No article text was recorded for this version.
reasoning token sparsity
Version 1 of 117 papers27 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Beyond Magnitude: Leveraging Direction of RLVR Updates for LLM Reasoning
- Blog: LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
- Blog: Reinforcement Learning with Promising Tokens for Large Language Models
- Blog: Selective Preference Optimization via Token-Level Reward Function Estimation
- Blog: Capture the Key in Reasoning to Enhance CoT Distillation Generalization
- Blog: The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
- Blog: Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
- Blog: Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
- Blog: Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
- Blog: Edit-Wise Preference Optimization for Grammatical Error Correction
- Blog: R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
- Blog: Experience Augmented Policy Optimization for LLM Reasoning
- Blog: Group Critical-token Policy Optimization for Autoregressive Image Generation
- Blog: Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
- Blog: SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
- Blog: Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- Blog: AttExplainer: Explain Transformer via Attention by Reinforcement Learning
History & citation
Current · Permanent link
- This direction split from Sparse Optimization of Critical Reasoning Tokens (82% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_reasoning_token_sparsity_57a3c140,
title = {reasoning token sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reasoning-token-sparsity/rdr_57a3c1406792492a9de6fdfb6941bc9f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_reasoning_token_sparsity_57a3c140_v1,
title = {reasoning token sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reasoning-token-sparsity/rdr_57a3c1406792492a9de6fdfb6941bc9f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}