most citedRedCode: Risky Code Execution and Generation Benchmark for Code Agents

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

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

Xin Xu, Ke Cheng, Hao Wang +11

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 full…