Reasoning under uncertainty in humans and language models
cs.LG
Submitted: 2026-02-09
Updated: 2026-11-16
Terminology
Sources
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
- OpenAI o1 System Card
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Competitive Programming with Large Reasoning Models
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Reasoning Models Don't Always Say What They Think
- Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
- The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
- Levels of Analysis for Large Language Models
- Finetuned Language Models Are Zero-Shot Learners
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Turning large language models into cognitive models
- In-context Reinforcement Learning with Algorithm Distillation
- Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
- AgentBench: Evaluating LLMs as Agents
- A Survey of In-Context Reinforcement Learning
- In-context learning agents are asymmetric belief updaters
- Do LLM Agents Have Regret? A Case Study in Online Learning and Games
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning