Think Less, Locally: Local Preference Learning for Reasoning Compression
cs.AI, cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/MuyaoYuan/LoCo
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Program Synthesis with Large Language Models
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
- Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria
- Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
- Efficient Reasoning with Balanced Thinking
- Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
- Mitigating Overthinking through Reasoning Shaping
- Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
- SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
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