Reproduce “Adversarial Speculative Reasoning Improves Long Horizon Agents” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hongyin Luo, Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit, Jeff Krapf, Dana Wensberg, Jack O’Brien
Adversarial Speculative Reasoning trains a draft model to propose undesirable framings at selected decisions, prompting the target to write its decision at the start of a fresh verification block. This can change precision in the context without changing the target distribution under exact rejection sampling. On DeepSWE, GLM-5.3-NVFP4 pass rate rose from 60.6% to 67.6%; gains are supported only in tested settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.