7 papers
Reasoning & Test-Time Compute
Chains, trees, atoms, and System-2 thinking that trade compute for correctness.
- Papers
- 7
- Read time
- 2.0h
- Avg length
- 17m
Hierarchical Reasoning Model
A 27M-parameter brain-inspired recurrent network that reasons inside its hidden state — no chain-of-thought, no pretraining, just 1000 examples — and beats giant LLMs on Sudoku, mazes, and ARC-AGI.
- Read
- 22 min
- Source
- arXiv:2506.21734
Atom of Thoughts for Markov LLM Test-Time Scaling
Instead of dragging the entire reasoning history forward at every step, AOT repeatedly rewrites a hard question into a smaller, self-contained "atomic" question — so the model spends all its compute on the problem in front of it, not on re-reading its own past work.
- Read
- 16 min
- Source
- arXiv:2502.12018
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
Insight-V teaches vision-language models to reason like OpenAI o1 by (a) auto-generating long step-by-step reasoning data with no human labelers and (b) splitting the job across two specialized agents — one that reasons and one that judges-and-summarizes — instead of asking a single model to do both.
- Read
- 16 min
- Source
- arXiv:2408.12637
Proof of Thought: Neurosymbolic Program Synthesis for Robust and Interpretable Reasoning
Instead of trusting an LLM's free-text reasoning, make it emit a structured JSON "program" of facts and rules, compile that into formal logic, and let a theorem prover (Z3) decide the answer — so the conclusion is *provable*, not just plausible.
- Read
- 16 min
- Source
- arXiv:2409.17270
Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks
Take a small open-weight LLM, teach it to diagnose 5G network faults by first feeding it structured reasoning traces (SFT) and then rewarding it for correct diagnoses (GRPO), and a 1.5B model beats a 70B reasoning model at telecom root-cause analysis.
- Read
- 16 min
The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest
When you infer a rule from a few examples, the rule most likely to keep working on new cases is not the *shortest* one (Occam's Razor / compression) but the *weakest* one — the rule that commits to the least and stays compatible with the most possibilities.
- Read
- 14 min
- Source
- arXiv:2301.12987
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
The "thinking out loud" that o1/R1-style models do at inference time is best understood as an *internalized search* over solutions — and this paper lays out the theory plus a concrete train-it-yourself pipeline (synthetic search traces + reinforcement learning) for getting a single model to do that search by itself.
- Read
- 22 min
- Source
- arXiv:2501.04682