PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
cs.AI, cs.LG, math.ST, stat.TH
Submitted: 2025-10-10
Updated: 2026-11-14
Terminology
Sources
- Conformal Risk Control
- Evaluating Large Language Models Trained on Code
- Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
- Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
- Thinker: Learning to Think Fast and Slow
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Thinkless: LLM Learns When to Think
- Reasoning with Language Model is Planning with World Model
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- FlashThink: An Early Exit Method For Efficient Reasoning
- A New Confidence Interval for the Mean of a Bounded Random Variable
- DynamicMind: A Tri-Mode Thinking System for Large Language Models
- ThinkSwitcher: When to Think Hard, When to Think Fast
- Reasoning Models Can Be Effective Without Thinking
- RouteLLM: Learning to Route LLMs with Preference Data
- Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners
- A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents