SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
