SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
[Sztuczna inteligencja] Autorzy: Xinyue Zeng, Jiawei Zhang, Yujun Yan i 1 więcej
Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon reasoning with local admissibility, and as a design principle for structural priors in less formal reasoning tasks. Motivated by this analysis, we propose SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horiz…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja