Context Awesome

awesome-efficient-reasoning-llms

github.com/eclipsess/awesome-efficient-reasoning-llms ↗

[TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

771

GitHub Stars

196

Curated Resources

9

Categories

5 hours ago

Last Refreshed

📢 NewsSection I: RL with Length Reward DesignSection II: SFT with Variable-Length CoT DataSection III: Compressing Reasoning Steps into Fewer Latent RepresentationSection IV: Dynamic Reasoning Paradigm during InferenceSection V: Prompt-Guided Efficient ReasoningSection VI: Prompts Attribute-Driven Reasoning RoutingSection VII: Reasoning Abilities via Efficient Training Data and Model CompressionSection VIII: Evaluation and Benchmark

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me section iv: dynamic reasoning paradigm during inference resources from awesome-efficient-reasoning-llms"

Installation instructions →

What's inside

Section IV: Dynamic Reasoning Paradigm during Inference

Section I: RL with Length Reward Design

Section II: SFT with Variable-Length CoT Data

Section III: Compressing Reasoning Steps into Fewer Latent Representation

Section VIII: Evaluation and Benchmark

Section V: Prompt-Guided Efficient Reasoning

Section VI: Prompts Attribute-Driven Reasoning Routing

Section VII: Reasoning Abilities via Efficient Training Data and Model Compression

Showing a sample of 196 resources. View the full list on GitHub →