跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.25230 · v3

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

首次提交 2026-05-25 03:32
版本更新 2026-11-07 06:08
雷达观测 2026-11-10 10:11
arXiv ↗PDF ↗

摘要

Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories with a latent dynamical system. We argue that the inference-time behaviour of these architectures is best understood as approximate inference over latent reasoning trajectories, with deterministic recursion as the one-particle, zero-noise limit. We make this view operational through guided reasoning: stochastic perturbations of the reasoning dynamics propose neighbouring trajectories, and the model's existing early-stopping head reweights them online. The framework yields three diagnostics computable from inference traces: local stability, guide alignment, with a label-free necessary condition, and cloud-token entropy. These predict whether the procedure will help and which of its outputs to trust. On Sudoku-Extreme it lifts exact-solve accuracy from 85.9%85.9\% to 98.0%98.0\% without retraining, and on PPBench, a four-type pencil-puzzle benchmark, from 62.5%62.5\% to 77.9%77.9\% with no tuning; on Maze-Hard the diagnostics flag a misaligned guide, as validation performance later confirms. The same machinery thus characterises both when recursive reasoning has room to improve at the trajectory level and when the model's internal guide can recover said improvements. Code is available at `https://github.com/digiLab-ai/bigr`.

作者备注:Accepted at NeurIPS 2026, main track. An earlier version was presented at the ICML 2026 Workshop on Structured Probabilistic Inference and Generative Modeling (SPIGM), Seoul. Code: https://github.com/digiLab-ai/bigr

期刊信息:Advances in Neural Information Processing Systems 40 (NeurIPS 2026)

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-07 06:08 · 最新观测版本

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories with a latent dynamical system. We argue that the inference-time behaviour of these architectures is best understood as approximate inference over latent reasoning trajectories, with deterministic recursion as the one-particle, zero-noise limit. We make this view operational through guided reasoning: stochastic perturbations of the reasoning dynamics propose neighbouring trajectories, and the model's existing early-stopping head reweights them online. The framework yields three diagnostics computable from inference traces: local stability, guide alignment, with a label-free necessary condition, and cloud-token entropy. These predict whether the procedure will help and which of its outputs to trust. On Sudoku-Extreme it lifts exact-solve accuracy from 85.9%85.9\% to 98.0%98.0\% without retraining, and on PPBench, a four-type pencil-puzzle benchmark, from 62.5%62.5\% to 77.9%77.9\% with no tuning; on Maze-Hard the diagnostics flag a misaligned guide, as validation performance later confirms. The same machinery thus characterises both when recursive reasoning has room to improve at the trajectory level and when the model's internal guide can recover said improvements. Code is available at `https://github.com/digiLab-ai/bigr`.

查看此版本解读 →查看此版本原文 ↗