BFS-PO: Best-First Search for Large Reasoning Models
cs.CL, cs.AI
Submitted: 2026-02-16
Updated: 2026-11-09
Code: https://github.com/aimagelab/BFS-PO
Terminology
Sources
- First Finish Search: Efficient Test-Time Scaling in Large Language Models
- The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
- Soft Tokens, Hard Truths
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Concise Reasoning via Reinforcement Learning
- Efficiently Scaling LLM Reasoning with Certaindex
- The Llama 3 Herd of Models
- Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
- ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
- Large Concept Models: Language Modeling in a Sentence Representation Space
- Solving Quantitative Reasoning Problems with Language Models
- ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
- Understanding R1-Zero-Like Training: A Critical Perspective
- Large Language Model Guided Tree-of-Thought
- O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
- s1: Simple test-time scaling
- Proximal Policy Optimization Algorithms
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data