arXiv Statistics ML
RL unknotter, hard unknots and unknotting number
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Oct 8
Computations of the slice genus and the unknotting number of links via machine learning
arXiv:2610.10206v1 Announce Type: cross Abstract: Links are disjoint unions of circles smoothly embedded in $S^3$. We use reinforcement learning and Bayesian optimisation to obtain new upper bounds o...
arXiv AI
Oct 2
HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models
HyperGuide introduces a hyperbolic geometric signal to guide multi-step reasoning in large language models, addressing the trade-off between efficient single-pass generation and computationally heavy tree-search methods. By projecting LLM hidden states into hyperbolic space, the approach leverages the space’s asymmetry—compact near the origin and exponentially expanding toward the boundary—to encode solution proximity and branch differentiation. A lightweight head and a fine-tuned low-rank adapter use this signal to improve reasoning accuracy, especially on deeper reasoning chains, with consistent gains across multiple benchmarks.
arXiv AI
Jun 15
Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories
arXiv:2511. 07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS).
arXiv Machine Learning
Jun 16
Using Reinforcement Learning to Optimize the Global and Local Crossing Number
arXiv:2509. 06108v2 Announce Type: replace-cross Abstract: Graph drawing concerns the algorithmic visualization of graphs.
arXiv AI
Oct 2
New Snake-in-the-Box Records via Snakepit Surgery and Learned Construction
The paper reports a new record for the snake-in-the-box problem, presenting a length‑191 snake in the 9‑dimensional hypercube, surpassing the previous 190‑length record that had stood for 14 years. It also establishes new lower bounds for dimensions 10 through 13. The authors introduce a novel search technique called snakepits, which expands the search space by considering collections of disjoint snakes, and propose a new benchmark, Snakepit‑in‑the‑Box, that evaluates maximal edge counts across multiple components. Additionally, they present Beam Anchor, a learned construction algorithm that generates 100 inequivalent length‑190 snakes in dimension 9.
arXiv AI
Aug 11
Branch2Skill: Efficient Skill Evolution Through Reasoning Trees
arXiv:2608. 08677v1 Announce Type: new Abstract: Skill evolution improves agent skills through feedback over time, with failed trajectories often providing informative signals by revealing incomplete or misleading behaviors.