Image de couverture de livre

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhong, Shuzhang, Huang, Haochen, Qiu, Shengxuan, Zuo, Pengfei, Wang, Runsheng, Li, Meng
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
par: Qiu, Shengxuan, et autres
Publié: (2026)

DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
par: Zhong, Shuzhang, et autres
Publié: (2026)

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding
par: Zhong, Shuzhang, et autres
Publié: (2024)

AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
par: Zhong, Shuzhang, et autres
Publié: (2024)

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
par: Wei, Linye, et autres
Publié: (2025)

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
par: Zhong, Shuzhang, et autres
Publié: (2025)

MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning
par: Zhi, Weihai, et autres
Publié: (2025)

Continuous Chain of Thought Enables Parallel Exploration and Reasoning
par: Gozeten, Halil Alperen, et autres
Publié: (2025)

Accelerated Diffusion Models via Speculative Sampling
par: De Bortoli, Valentin, et autres
Publié: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
par: Yang, Rubing, et autres
Publié: (2025)

SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
par: Chang, Chi-Chih, et autres
Publié: (2026)

Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling
par: Cheshmi, Seyyed Saeid, et autres
Publié: (2025)

DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management
par: Su, Xuerui, et autres
Publié: (2025)

FastEagle: Cascaded Drafting for Accelerating Speculative Decoding
par: Huang, Haiduo, et autres
Publié: (2025)

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
par: Jiang, Yan, et autres
Publié: (2026)

Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
par: Zabounidis, Renos, et autres
Publié: (2025)

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
par: Sun, Shuoyang, et autres
Publié: (2026)

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
par: Zhao, Yilong, et autres
Publié: (2025)

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
par: Li, Ye, et autres
Publié: (2025)

Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models
par: Wei, Linye, et autres
Publié: (2025)

From Laws to Motivation: Guiding Exploration through Law-Based Reasoning and Rewards
par: Chen, Ziyu, et autres
Publié: (2024)

Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs
par: Huang, Ruiquan, et autres
Publié: (2026)

Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptation
par: Liu, Haochen, et autres
Publié: (2024)

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
par: Ahmed, Ammar, et autres
Publié: (2025)

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
par: Dong, Peijie, et autres
Publié: (2024)

CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
par: Wu, Junda, et autres
Publié: (2025)

Improved Bounds for Reward-Agnostic and Reward-Free Exploration
par: Ridel, Oran, et autres
Publié: (2026)

Quasar: Quantized Self-Speculative Acceleration for Rapid Inference via Memory-Efficient Verification
par: Huang, Guang, et autres
Publié: (2026)

Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors
par: Xing, Wei W., et autres
Publié: (2026)

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
par: Zhou, Yang, et autres
Publié: (2025)

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
par: Fu, Zizhuo, et autres
Publié: (2026)

Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
par: Iso, Hayate, et autres
Publié: (2026)

Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
par: Williams, Jonathan, et autres
Publié: (2026)

SSR: Speculative Parallel Scaling Reasoning in Test-time
par: Chu, Yuanlin, et autres
Publié: (2025)

FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies
par: He, Tianqi, et autres
Publié: (2025)

Breaking the Factorization Barrier in Diffusion Language Models
par: Li, Ian, et autres
Publié: (2026)

Accelerating Time Series Foundation Models with Speculative Decoding
par: Subbaraman, Pranav, et autres
Publié: (2025)

Scalable Chain of Thoughts via Elastic Reasoning
par: Xu, Yuhui, et autres
Publié: (2025)

Rethinking Chain-of-Thought Reasoning for Videos
par: Zhong, Yiwu, et autres
Publié: (2025)

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
par: Zhang, Xichen, et autres
Publié: (2025)