DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning

arXiv:2607.22602 · cs.AI · Submitted 2026-06-12 · Read on arXiv

cs.AI

Submitted: 2026-06-12

Updated: 2026-10-21

Comments: EMNLP 2026 Workshop UncertaiNLP

Code: https://github.com/txyang1/deeplook

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 3× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
• Efficient Reasoning Models: A Survey
• Deep Think with Confidence
• ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty
• Large Language Models are Zero-Shot Reasoners
• MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
• Efficient Inference for Large Reasoning Models: A Survey
• Self-Refine: Iterative Refinement with Self-Feedback
• gpt-oss-120b & gpt-oss-20b Model Card
• A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• DeepPrune: Parallel Scaling without Inter-trace Redundancy
• TokenSkip: Controllable Chain-of-Thought Compression in LLMs
• Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards
• $\phi$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
• Chain of Draft: Thinking Faster by Writing Less
• Qwen3 Technical Report

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