AutoThink – Boosts local LLM performance with adaptive reasoning
I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical…
In plain words
AutoThink is a technique that improves the performance of local language models by dynamically allocating computational resources based on query complexity. Instead of using the same amount of thinking time for all queries, it classifies them as high or low complexity and assigns between 20-90% of tokens accordingly. The method also uses steering vectors to guide reasoning patterns toward accuracy and self-correction. It works with any local reasoning model and has shown significant improvements on reasoning benchmarks while using fewer tokens than baseline approaches.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical accuracy, self-correction, and thorough exploration. Results on DeepSeek-R1-Distill-Qwen-1.5B: - GPQA-Diamond: 31.06% vs 21.72% baseline (+43% relative improvement) - MMLU-Pro: 26.38% vs 25.58% baseline - Uses fewer tokens than baseline approaches Works with any local reasoning model - DeepSeek, Qwen, custom fine-tuned models. No API dependencies. The technique builds on two things I developed: an adaptive classification framework that can learn new complexity categories without retraining, and an open source implementation of Pivotal Token Search. Technical paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5253327 Code and examples: https://github.com/codelion/optillm/tree/main/optillm/autoth... PTS implementation: https://github.com/codelion/pts I'm curious about your thoughts on adaptive resource allocation for AI reasoning. Have you tried similar approaches with your local models?
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
