Image de couverture de livre

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Qi, Yang, Shouqing, Gao, Lirong, Chen, Hao, Hu, Xiaomeng, Chen, Jinglei, Wang, Jiexiang, Guo, Sheng, Zheng, Bo, Wang, Haobo, Zhao, Junbo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
par: Yu, Zewei, et autres
Publié: (2026)

DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
par: Zhang, Qi, et autres
Publié: (2026)

FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts
par: Wang, Xinyi, et autres
Publié: (2025)

Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
par: Yang, Shenzhi, et autres
Publié: (2025)

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
par: Chen, Hao, et autres
Publié: (2025)

Process Reward Models That Think
par: Khalifa, Muhammad, et autres
Publié: (2025)

VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
par: Yin, Tengjiao, et autres
Publié: (2026)

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
par: Shen, Zhanming, et autres
Publié: (2025)

PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization
par: Ding, Ruiyi, et autres
Publié: (2026)

RECOST: External Knowledge Guided Data-efficient Instruction Tuning
par: Zhang, Qi, et autres
Publié: (2024)

FlowTS: Time Series Generation via Rectified Flow
par: Hu, Yang, et autres
Publié: (2024)

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
par: Wang, Binghai, et autres
Publié: (2026)

Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
par: Lee, Unggi, et autres
Publié: (2026)

D.Va: Validate Your Demonstration First Before You Use It
par: Zhang, Qi, et autres
Publié: (2025)

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling
par: Sun, Hao, et autres
Publié: (2025)

Heat Diffusion Models -- Interpixel Attention Mechanism
par: Zhang, Pengfei, et autres
Publié: (2025)

UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning
par: Liang, Zhiyu, et autres
Publié: (2023)

PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding
par: Che, Lirong, et autres
Publié: (2026)

Elliptic constant cycle curves on Kummer surfaces
par: Huang, Jiexiang
Publié: (2025)

DORY: Deliberative Prompt Recovery for LLM
par: Gao, Lirong, et autres
Publié: (2024)

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
par: Ye, Chenlu, et autres
Publié: (2025)

SPICE : Leveraging Soft Probabilistic Causal Intervention for Breast Ultrasound Tumor Segmentation
par: Haobo Chen, et autres
Publié: (2026)

PRInTS: Reward Modeling for Long-Horizon Information Seeking
par: Lee, Jaewoo, et autres
Publié: (2025)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
par: Gan, Siyuan, et autres
Publié: (2026)

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
par: Mou, Zhiyu, et autres
Publié: (2025)

GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching
par: Wang, Haoran, et autres
Publié: (2024)

From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
par: Chen, Hao, et autres
Publié: (2026)

Symbolic Analysis of Grover Search Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization
par: Chen, Min, et autres
Publié: (2025)

A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
par: Zheng, Congmin, et autres
Publié: (2025)

Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
par: Wei, Qi, et autres
Publié: (2024)

PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference
par: Sharma, Rituraj, et autres
Publié: (2026)

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
par: Wang, Yiding, et autres
Publié: (2025)

Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
par: Zhang, Zheng, et autres
Publié: (2025)

Comments on: “Biallelic ELOVL1 Variants Are Linked to Hypomyelinating Leukodystrophy, Movement Disorder, and Ichthyosis”
par: DuJiang Yang, et autres
Publié: (2025)

Mitochondrial Dysfunction in Viral Neuropathogenesis: Unaddressed Challenges From Mechanism to Therapeutic Translation
par: DuJiang Yang, et autres
Publié: (2025)

The elusive predictors of anterior cruciate ligament failure in the young: Null findings in registry data
par: DuJiang Yang, et autres
Publié: (2026)

From Single‐Cell Atlas to Functional Validation: Critical Next Steps for Understanding Tip Cell‐Mediated Communication in the Injured Spinal Cord
par: DuJiang Yang, et autres
Publié: (2025)

The road to therapy for myeloid sarcoma: navigating the complexities of subclonal MAPK / ERK mutations and clonal evolution
par: DuJiang Yang, et autres
Publié: (2025)

Cerebral Dopamine Neurotrophic Factor in Dorsal Root Ganglia Neurons: A Critical Appraisal of Mechanisms and Unexplored Pathways
par: DuJiang Yang, et autres
Publié: (2025)

Targeting the Hyperglycemic Pre‐Metastatic Niche to Prevent Breast Cancer Bone Metastasis: Mechanisms and Therapeutic Strategies
par: DuJiang Yang, et autres
Publié: (2025)