ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models
cs.AI, cs.CL
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/js-lee-AI/ThinkFuse
Sources
- EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
- EXAONE Deep: Reasoning Enhanced Language Models
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Multi-Layer GRPO: Enhancing Reasoning and Self-Correction in Large Language Models
- Efficiently Scaling LLM Reasoning with Certaindex
- StyleBench: Evaluating thinking styles in Large Language Models
- A Study on Thinking Patterns of Large Reasoning Models in Code Generation
- Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
- Ministral 3
- Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
- Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
- Qwen3 Technical Report
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems