-
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Paper • 2505.04842 • Published • 12 -
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Paper • 2505.04588 • Published • 65 -
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Paper • 2504.21776 • Published • 59 -
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Paper • 2505.01441 • Published • 39
Collections
Discover the best community collections!
Collections including paper arxiv:2505.04842
-
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Paper • 2411.02337 • Published • 36 -
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Paper • 2411.04996 • Published • 51 -
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
Paper • 2411.03562 • Published • 68 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 47
-
ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 70 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 41 -
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 50 -
Best Practices and Lessons Learned on Synthetic Data for Language Models
Paper • 2404.07503 • Published • 31
-
CoRAG: Collaborative Retrieval-Augmented Generation
Paper • 2504.01883 • Published • 9 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 43 -
Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
Paper • 2504.10068 • Published • 30 -
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Paper • 2504.10481 • Published • 85
-
FLAME: Factuality-Aware Alignment for Large Language Models
Paper • 2405.01525 • Published • 28 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 43 -
Transformers Can Do Arithmetic with the Right Embeddings
Paper • 2405.17399 • Published • 54 -
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
Paper • 2405.18991 • Published • 12
-
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Paper • 2505.04842 • Published • 12 -
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Paper • 2505.04588 • Published • 65 -
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Paper • 2504.21776 • Published • 59 -
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Paper • 2505.01441 • Published • 39
-
CoRAG: Collaborative Retrieval-Augmented Generation
Paper • 2504.01883 • Published • 9 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 43 -
Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
Paper • 2504.10068 • Published • 30 -
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Paper • 2504.10481 • Published • 85
-
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Paper • 2411.02337 • Published • 36 -
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Paper • 2411.04996 • Published • 51 -
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
Paper • 2411.03562 • Published • 68 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 47
-
FLAME: Factuality-Aware Alignment for Large Language Models
Paper • 2405.01525 • Published • 28 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 43 -
Transformers Can Do Arithmetic with the Right Embeddings
Paper • 2405.17399 • Published • 54 -
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
Paper • 2405.18991 • Published • 12
-
ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 70 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 41 -
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 50 -
Best Practices and Lessons Learned on Synthetic Data for Language Models
Paper • 2404.07503 • Published • 31