Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Paper
•
2412.18319
•
Published
•
40
Reasoning, Thinking, RL and Test-Time Scaling
-
-
Token-Budget-Aware LLM Reasoning
Paper • 2412.18547 • Published • 47 -
Efficiently Serving LLM Reasoning Programs with Certaindex
Paper • 2412.20993 • Published • 38 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 48 -
OpenAI o1 System Card
Paper • 2412.16720 • Published • 34 -
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
Paper • 2412.17498 • Published • 22 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19 -
Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability
Paper • 2411.19943 • Published • 63 -
MALT: Improving Reasoning with Multi-Agent LLM Training
Paper • 2412.01928 • Published • 45 -
Mars-PO: Multi-Agent Reasoning System Preference Optimization
Paper • 2411.19039 • Published • 1 -
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
Paper • 2410.22304 • Published • 18 -
o1-Coder: an o1 Replication for Coding
Paper • 2412.00154 • Published • 45 -
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Paper • 2411.14405 • Published • 62 -
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Paper • 2410.09671 • Published • 1 -
SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
Paper • 2411.11053 • Published • 4 -
Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS
Paper • 2411.18478 • Published • 38 -
Reverse Thinking Makes LLMs Stronger Reasoners
Paper • 2411.19865 • Published • 23 -
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Paper • 2411.16579 • Published • 3 -
Vision-Language Models Can Self-Improve Reasoning via Reflection
Paper • 2411.00855 • Published • 5 -
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Paper • 2411.04282 • Published • 36 -
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
Paper • 2411.14432 • Published • 26 -
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Paper • 2411.18203 • Published • 37 -
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Paper • 2411.16489 • Published • 49 -
VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
Paper • 2411.14794 • Published • 13 -
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper • 2411.10442 • Published • 81 -
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
Paper • 2410.02884 • Published • 55 -
LLaVA-o1: Let Vision Language Models Reason Step-by-Step
Paper • 2411.10440 • Published • 124 -
Large Language Models Can Self-Improve in Long-context Reasoning
Paper • 2411.08147 • Published • 67 -
Self-Consistency Preference Optimization
Paper • 2411.04109 • Published • 19 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 277 -
URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics
Paper • 2501.04686 • Published • 54 -
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
Paper • 2501.04682 • Published • 98 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 45 -
Test-time Computing: from System-1 Thinking to System-2 Thinking
Paper • 2501.02497 • Published • 46 -
Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
Paper • 2501.01904 • Published • 34 -
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Paper • 2412.21187 • Published • 42 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 102 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 99 -
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning
Paper • 2501.06458 • Published • 32 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 66 -
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 49 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 40 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 384 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 113 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 120 -
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 59 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 151 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 120 -
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Paper • 2502.06773 • Published • 1 -
Competitive Programming with Large Reasoning Models
Paper • 2502.06807 • Published • 70 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 114 -
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong
Paper • 2501.09775 • Published • 34 -
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
Paper • 2501.12368 • Published • 46 -
Reasoning Language Models: A Blueprint
Paper • 2501.11223 • Published • 33 -
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Paper • 2501.12570 • Published • 28 -
Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
Paper • 2501.13007 • Published • 20 -
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
Paper • 2501.13926 • Published • 42 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Chain-of-Retrieval Augmented Generation
Paper • 2501.14342 • Published • 56 -
RL + Transformer = A General-Purpose Problem Solver
Paper • 2501.14176 • Published • 28 -
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 30 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 36 -
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper • 2501.18585 • Published • 61 -
Large Language Models Think Too Fast To Explore Effectively
Paper • 2501.18009 • Published • 24 -
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper • 2501.19324 • Published • 39 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 60 -
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
Paper • 2502.13124 • Published • 6 -
ACECODER: Acing Coder RL via Automated Test-Case Synthesis
Paper • 2502.01718 • Published • 28 -
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
Paper • 2502.02508 • Published • 23 -
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
Paper • 2502.02584 • Published • 17 -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 61 -
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking
Paper • 2502.02339 • Published • 22 -
On Teacher Hacking in Language Model Distillation
Paper • 2502.02671 • Published • 18 -
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
Paper • 2502.03275 • Published • 17 -
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
Paper • 2502.03544 • Published • 44 -
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Paper • 2502.03860 • Published • 24 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 138 -
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 22 -
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Paper • 2502.04404 • Published • 24 -
Generating Symbolic World Models via Test-time Scaling of Large Language Models
Paper • 2502.04728 • Published • 19 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 61 -
Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
Paper • 2502.06060 • Published • 38 -
ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
Paper • 2502.06772 • Published • 21 -
CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Paper • 2502.07316 • Published • 48 -
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Paper • 2502.07374 • Published • 39 -
Teaching Language Models to Critique via Reinforcement Learning
Paper • 2502.03492 • Published • 24 -
Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance
Paper • 2502.08127 • Published • 54 -
Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Paper • 2502.06533 • Published • 18 -
An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging
Paper • 2502.09056 • Published • 31 -
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
Paper • 2502.09604 • Published • 35 -
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
Paper • 2502.09621 • Published • 27 -
Logical Reasoning in Large Language Models: A Survey
Paper • 2502.09100 • Published • 22 -
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
Paper • 2502.09390 • Published • 16 -
Typhoon T1: An Open Thai Reasoning Model
Paper • 2502.09042 • Published • 16 -
CoT-Valve: Length-Compressible Chain-of-Thought Tuning
Paper • 2502.09601 • Published • 14 -
Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
Paper • 2502.08680 • Published • 11 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 34 -
S*: Test Time Scaling for Code Generation
Paper • 2502.14382 • Published • 63 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 17 -
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 28 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 74 -
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper • 2502.14768 • Published • 48 -
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
Paper • 2502.14669 • Published • 14 -
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
Paper • 2502.10458 • Published • 35 -
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper • 2502.12853 • Published • 29 -
Thinking Preference Optimization
Paper • 2502.13173 • Published • 17 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 84 -
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Paper • 2502.19361 • Published • 28 -
LightThinker: Thinking Step-by-Step Compression
Paper • 2502.15589 • Published • 28 -
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper • 2503.16219 • Published • 46 -
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
Paper • 2502.19735 • Published • 9 -
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Paper • 2502.16111 • Published • 9 -
TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning
Paper • 2502.15425 • Published • 9 -
The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer
Paper • 2502.15631 • Published • 9 -
Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models
Paper • 2502.16033 • Published • 17 -
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
Paper • 2502.17407 • Published • 25 -
VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model
Paper • 2502.18906 • Published • 12 -
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 22 -
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 108 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 76 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 47 -
Process-based Self-Rewarding Language Models
Paper • 2503.03746 • Published • 39 -
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Paper • 2502.20730 • Published • 39 -
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Paper • 2503.01307 • Published • 37 -
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
Paper • 2502.20396 • Published • 15 -
Language Models can Self-Improve at State-Value Estimation for Better Search
Paper • 2503.02878 • Published • 9 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 66 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 21