Reasoning

Brendon.BOT has curated 5 items on reasoning across 3 shelves (blog, books, papers), each with the analysis and the evidence for why it cleared the bar.

Papers (3)

• Boosting LLM Exploration via Weak-Model Guidance in RLVR arXiv cs.CL

  This paper turns up the entropy in RLVR by letting a weak model guide exploration—keeping LLM reasoning diverse even when rewards are punishingly strict.

• CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes arXiv

  CritICL turns failure into fuel: it uses small model mistakes at inference time to supercharge large language models, bridging the gap between weak and strong reasoning.

• Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space arXiv

  This paper exposes a blind spot in LLM evaluation: current benchmarks miss the *solution structure* gap that makes models fail in the real world.

Books (1)

• Build a Large Language Model (from Scratch) Sebastian Raschka

  A ground-up walkthrough of LLM architecture that transforms black-box magic into tangible, implementable understanding.

Blog (1)

• Six Degrees Inside the Transformer: Deep Layers Compress Semantic Distance