SmartThinker: Learning High-Density Reasoning via Step-Level Token Allocation
cs.AI, cs.CL
Submitted: 2025-07-06
Updated: 2026-11-14
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Training Language Models to Reason Efficiently
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
- Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
- Thinkless: LLM Learns When to Think
- Efficient Reasoning Models: A Survey
- Efficiently Scaling LLM Reasoning with Certaindex
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Token-Budget-Aware LLM Reasoning
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Measuring Mathematical Problem Solving With the MATH Dataset
- ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
- OpenAI o1 System Card
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- RACE: Large-scale ReAding Comprehension Dataset From Examinations
- Understanding R1-Zero-Like Training: A Critical Perspective
- Decoupled Weight Decay Regularization
- AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
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