Learning Composable Chains-of-Thought
cs.CL, cs.AI
Submitted: 2025-05-28
Updated: 2026-08-30
Code: https://github.com/fc2869/composable_cot
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- s1: Simple test-time scaling
- GPT-4o System Card
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen2.5 Technical Report
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Training Large Language Models to Reason in a Continuous Latent Space
- Meta Reasoning for Large Language Models
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
- Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning
- Realistic Evaluation of Model Merging for Compositional Generalization
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering