SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

  • 类型:arxiv
  • 标识:2609.30192
  • 链接:https://arxiv.org/abs/2609.30192
  • 主分类:engineering
  • 形态:method
  • TLDR: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 admi
  • 待LLM分类:是
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-29-agent-rag-longcontext-candidates.json