Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Paper
• 2505.04842 • Published
• 12
RL
-
-
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 -
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
Paper • 2504.20708 • Published • 23 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 139 -
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Paper • 2504.10481 • Published • 85 -
Iterative Self-Training for Code Generation via Reinforced Re-Ranking
Paper • 2504.09643 • Published • 34 -
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
Paper • 2504.20157 • Published • 37 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 63 -
Inference-Time Scaling for Generalist Reward Modeling
Paper • 2504.02495 • Published • 58 -
ToolRL: Reward is All Tool Learning Needs
Paper • 2504.13958 • Published • 49 -
T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models
Paper • 2504.04718 • Published • 43 -
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 113 -
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 81 -
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
Paper • 2505.02847 • Published • 29 -
Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
Paper • 2505.00234 • Published • 26 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 88