Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems

Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while fully evaluating every intermediate version can exhaust the budget before those sequences yield a verified improvement. We introduce (), which drafts executable successor agents before their predecessors are fully evaluated, while requiring complete verification before adoption. Verification-Aware Tree Search (VATS) allocates the budget between further edits and outstanding checks using the predicted verified return of a continuation. Group Verification Optimization (GVO) learns the improver from completed searches while keeping the real evaluator fixed. In the main scientific comparison, terminal gains exceed Janus by 33.3%–40.0%. Additional evaluations outperform Janus in all 50 scientific backbone–task pairs and exceed MetaRSI-v1 by 1.85%–2.38% in macro-average system score across twenty backbones. Coding-validation success reaches 69.4% versus HGM's 64.3% at a 20.8% lower target-cost index. These results demonstrate the efficacy of the proposed approach. Code is available in https://anonymous.4open.science/r/SpecRSI-739D/.