Imagen de Portada

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Su, Yi, Yu, Dian, Song, Linfeng, Li, Juntao, Mi, Haitao, Tu, Zhaopeng, Zhang, Min, Yu, Dong
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
por: Liu, Xiaoyuan, et al.
Publicado: (2025)

Teaching LLMs to Refine with Tools
por: Yu, Dian, et al.
Publicado: (2024)

Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
por: Wang, Ante, et al.
Publicado: (2025)

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
por: Ding, Yuyang, et al.
Publicado: (2025)

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
por: Yu, Dian, et al.
Publicado: (2024)

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
por: Wang, Yue, et al.
Publicado: (2025)

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
por: Yu, Dian, et al.
Publicado: (2025)

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
por: He, Zhiwei, et al.
Publicado: (2025)

Verified Critical Step Optimization for LLM Agents
por: Li, Mukai, et al.
Publicado: (2026)

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
por: Dai, Runpeng, et al.
Publicado: (2025)

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
por: Tian, Ye, et al.
Publicado: (2024)

AgentV-RL: Scaling Reward Modeling with Agentic Verifier
por: Zhang, Jiazheng, et al.
Publicado: (2026)

CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
por: Liang, Zhenwen, et al.
Publicado: (2025)

LiteSearch: Efficacious Tree Search for LLM
por: Wang, Ante, et al.
Publicado: (2024)

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
por: Shen, Yiran, et al.
Publicado: (2025)

Inconsistent dialogue responses and how to recover from them
por: Zhang, Mian, et al.
Publicado: (2024)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
por: Wang, Peisong, et al.
Publicado: (2025)

Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
por: Zhang, Xin, et al.
Publicado: (2026)

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
por: Li, Gaotang, et al.
Publicado: (2026)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
por: Chen, Xingyu, et al.
Publicado: (2024)

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
por: Liu, Rui, et al.
Publicado: (2026)

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
por: Zhang, Yuheng, et al.
Publicado: (2025)

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
por: Liang, Tian, et al.
Publicado: (2025)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
por: Pavlenko, Kirill, et al.
Publicado: (2026)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
por: Wang, Xiyao, et al.
Publicado: (2024)

On-Policy RL with Optimal Reward Baseline
por: Hao, Yaru, et al.
Publicado: (2025)

When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
por: Fan, Mingyuan, et al.
Publicado: (2026)

A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
por: Li, Xiangci, et al.
Publicado: (2024)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
por: Gunjal, Anisha, et al.
Publicado: (2025)

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
por: Li, Ming, et al.
Publicado: (2025)

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling
por: Feng, Zhaopeng, et al.
Publicado: (2025)

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
por: Jiang, Yuxin, et al.
Publicado: (2026)

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
por: Zhou, Yujun, et al.
Publicado: (2025)

Sotopia-RL: Reward Design for Social Intelligence
por: Yu, Haofei, et al.
Publicado: (2025)

Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards
por: Jia, Ruipeng, et al.
Publicado: (2025)

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
por: Yu, Qinan, et al.
Publicado: (2026)

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
por: Das, Souvik, et al.
Publicado: (2024)

Collaborative decoding of critical tokens for boosting factuality of large language models
por: Jin, Lifeng, et al.
Publicado: (2024)

Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
por: Liu, Haolin, et al.
Publicado: (2026)

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
por: Tang, Xinyu, et al.
Publicado: (2025)