Chinese contentBehavioral Localization 方法让工具调用智能体更高效学习软技能
教智能体学技能不用整条轨迹都学，只挑 10% 关键位置就够，成功率还能涨 6 个多点，做 Agent 训练的可以看看。
#SpreadsheetBench
3 stories · 0 in 7 days · 2 in 30 days
Stories, products and papers tagged "SpreadsheetBench", newest first.
Oct 22
Oct 16
Self-Improving Agents Need Harness Edits Tested on Fresh Tasks
A strong small model with an evolved harness can outscore a larger model tuned only with skills, shifting attention from model choice to harness quality. Builders running self-modifying agents should gate every edit behind fresh-task evaluation and keep evaluators, permissions and emergency stops out of the agent's reach. The taxonomy of edits, from prompt changes to runtime code, gives teams a concrete checklist for admission policies.
Jul 24
Papers09:22
Chinese content工作流局部机制学习：结构化Agent技能的归因修复与知识复用这篇论文提出了WML方法，能精准定位Agent工作流失败节点并复用外部技能知识，在SpreadsheetBench和Compiler-Supported50上表现亮眼，比直接SkillAgent省不少token。