-
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 47 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 24 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 491
Collections
Discover the best community collections!
Collections including paper arxiv:2509.13761
-
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Paper • 2508.21113 • Published • 110 -
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Paper • 2508.16949 • Published • 22 -
EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper • 2508.21112 • Published • 77 -
UItron: Foundational GUI Agent with Advanced Perception and Planning
Paper • 2508.21767 • Published • 12
-
lusxvr/nanoVLM-222M
Image-Text-to-Text • 0.2B • Updated • 518 • 98 -
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 36 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88
-
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 54 -
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
Paper • 2410.01215 • Published • 39 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121 -
EuroLLM: Multilingual Language Models for Europe
Paper • 2409.16235 • Published • 29
-
Open Data Synthesis For Deep Research
Paper • 2509.00375 • Published • 70 -
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Paper • 2509.03403 • Published • 22 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 23 -
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
Paper • 2509.00930 • Published • 4
-
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 83 -
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench
Paper • 2508.20931 • Published • 15 -
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16
-
RL + Transformer = A General-Purpose Problem Solver
Paper • 2501.14176 • Published • 28 -
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 30 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 123 -
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
Paper • 2412.12098 • Published • 4
-
Transformers Can Do Arithmetic with the Right Embeddings
Paper • 2405.17399 • Published • 54 -
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79 -
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Paper • 2507.06181 • Published • 43
-
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 47 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 24 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 491
-
Open Data Synthesis For Deep Research
Paper • 2509.00375 • Published • 70 -
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Paper • 2509.03403 • Published • 22 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 23 -
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
Paper • 2509.00930 • Published • 4
-
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Paper • 2508.21113 • Published • 110 -
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Paper • 2508.16949 • Published • 22 -
EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper • 2508.21112 • Published • 77 -
UItron: Foundational GUI Agent with Advanced Perception and Planning
Paper • 2508.21767 • Published • 12
-
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 83 -
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench
Paper • 2508.20931 • Published • 15 -
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16
-
lusxvr/nanoVLM-222M
Image-Text-to-Text • 0.2B • Updated • 518 • 98 -
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 36 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88
-
RL + Transformer = A General-Purpose Problem Solver
Paper • 2501.14176 • Published • 28 -
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 30 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 123 -
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
Paper • 2412.12098 • Published • 4
-
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 54 -
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
Paper • 2410.01215 • Published • 39 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121 -
EuroLLM: Multilingual Language Models for Europe
Paper • 2409.16235 • Published • 29
-
Transformers Can Do Arithmetic with the Right Embeddings
Paper • 2405.17399 • Published • 54 -
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79 -
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Paper • 2507.06181 • Published • 43