Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
Paper
•
2407.20798
•
Published
•
24
Reinforcement learning
-
-
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 102 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 75 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 88 -
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
Paper • 2504.16078 • Published • 21 -
OTC: Optimal Tool Calls via Reinforcement Learning
Paper • 2504.14870 • Published • 35 -
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Paper • 2504.20571 • Published • 96 -
Thinkless: LLM Learns When to Think
Paper • 2505.13379 • Published • 50 -
Visual Agentic Reinforcement Fine-Tuning
Paper • 2505.14246 • Published • 32 -
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
Paper • 2505.11711 • Published • 11 -
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
Paper • 2505.14810 • Published • 62 -
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Paper • 2505.14625 • Published • 13 -
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
Paper • 2505.15776 • Published • 10 -
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
Paper • 2505.16483 • Published • 10 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 59 -
Synthetic Data RL: Task Definition Is All You Need
Paper • 2505.17063 • Published • 10 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 138 -
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 184 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 262 -
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper • 2506.14245 • Published • 42 -
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Paper • 2507.03112 • Published • 31 -
Pre-Trained Policy Discriminators are General Reward Models
Paper • 2507.05197 • Published • 39 -
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
Paper • 2507.05920 • Published • 11 -
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
Paper • 2507.13158 • Published • 24 -
The Invisible Leash: Why RLVR May Not Escape Its Origin
Paper • 2507.14843 • Published • 84 -
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization
Paper • 2507.14683 • Published • 131 -
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Paper • 2507.14295 • Published • 13 -
Geometric-Mean Policy Optimization
Paper • 2507.20673 • Published • 31 -
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
Paper • 2508.02150 • Published • 36 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 28 -
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Paper • 2508.08221 • Published • 47 -
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
Paper • 2508.08791 • Published • 16 -
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Paper • 2508.10751 • Published • 27 -
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 82 -
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Paper • 2508.16949 • Published • 22 -
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Paper • 2508.21113 • Published • 109 -
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Paper • 2509.02547 • Published • 217 -
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Paper • 2509.02522 • Published • 25 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 83 -
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Paper • 2509.06493 • Published • 11 -
Language Self-Play For Data-Free Training
Paper • 2509.07414 • Published • 28 -
Bootstrapping Task Spaces for Self-Improvement
Paper • 2509.04575 • Published • 5 -
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Paper • 2509.06949 • Published • 56 -
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Paper • 2509.06733 • Published • 31 -
RewardDance: Reward Scaling in Visual Generation
Paper • 2509.08826 • Published • 71 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 183 -
Single-stream Policy Optimization
Paper • 2509.13232 • Published • 33 -
Tree Search for LLM Agent Reinforcement Learning
Paper • 2509.21240 • Published • 86 -
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Paper • 2509.22576 • Published • 129 -
Variational Reasoning for Language Models
Paper • 2509.22637 • Published • 67 -
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
Paper • 2509.25760 • Published • 52 -
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper • 2509.22601 • Published • 29 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 46 -
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Paper • 2509.26628 • Published • 12 -
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 129 -
BroRL: Scaling Reinforcement Learning via Broadened Exploration
Paper • 2510.01180 • Published • 17 -
RLP: Reinforcement as a Pretraining Objective
Paper • 2510.01265 • Published • 37 -
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Paper • 2510.04996 • Published • 15 -
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 40 -
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper • 2510.03222 • Published • 43 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 223 -
Demystifying Reinforcement Learning in Agentic Reasoning
Paper • 2510.11701 • Published • 27