SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

Published
Source
arXiv
Paper number
1129
Field
Reasoning
arXiv ID
2609.30192

Key points

  • It defines long-horizon reasoning failures along two axes, exploration bias and compounding bias, and presents a theoretical analysis (Symbolic Closure Analysis).
  • Algebraic sparsification reduces spurious branches, while hyperbolic embedding provides dense depth-wise signals, each addressing one of the two biases.
  • It consistently outperformed existing methods across 12 benchmarks and 7 model families.
  • It achieved up to an 8-fold improvement on the real-world open Andrews-Curtis problem.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)