Tiny Interaction Models - Rajan Agarwal
Post-training a small open model to process typing as a live stream, so it can look things up while you write, hold what it finds, and stay quiet the rest of the time.
I post-trained Qwen3 30B-A3B into a text interaction model. It follows typing as a timestamped stream and chooses one action at each step: stay idle, mark a span, delegate a lookup, integrate a pending result, skip stale information, or respond. Most of the time, it stays quiet. The project started with a practical question about Thinking Machines' interaction models: what would the same idea look like in text, where the model sees partial drafts but should rarely intervene? The resulting model can mark relevant words, look up information while a sentence is still being written, hold onto…
saved by
related reading
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- Rajan Agarwalrajan.sh
- On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
- LLMs can invent their own compression - Rajan Agarwalrajan.sh
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- How not to do research - Rajan Agarwalrajan.sh
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- user_interactions.pdfself-distillation.github.io
- Base Models Know How to Reason, Thinking Models Learn Whenarxiv.org
- [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
- [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
- Scaling Activation Oracles to Trillion-Parameter Modelstransluce.org