works on
benchmark improvement 1data compilation 1executable agent training 1requirement-first synthesis 1task generation scaling 1

From the 1 of 15 linked papers with an AI index.

most citedBuilding Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing cs.SEShow all

1 paper · 1 filter

cs.SE2026

NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs

Jiarong Zhao, Zhikai Lei, Zhiheng Xi +5

The paper presents NexForge, a requirement‑first framework that automatically turns free‑form capability requirements into executable agent training tasks, scaling data generation…