software-agents

Tag

Cards List
#software-agents

HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference

Hugging Face Daily Papers ↗ · 2026-10-17 Cached

该论文提出层级分数后验恢复方法(HSPR),通过结合历史响应模式与自适应任务选择,仅用小子集即可高效估计软件代理在完整基准测试上的分数,在SWE-bench系列任务库上取得最低的平均与最大绝对误差。

0 favorites 0 likes
#software-agents

@matanSF: ProgramBench is a benchmark where agents must reproduce the observable behavior of real software, completely from scrat…

X AI KOLs Following ↗ · 2026-08-27 Cached

ProgramBench is a benchmark for agents to reproduce real software behavior from scratch. Factory is announced as the most advanced reverse-engineering system with breakthroughs in model-agnostic long-horizon agents.

0 favorites 0 likes
#software-agents

DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents

arXiv cs.AI ↗ · 2026-08-24 Cached

This paper introduces DreamBench-SWE, a benchmark for evaluating memory hygiene in multi-session software agents, and reports experimental results showing its ability to discriminate memory configurations and characterize performance.

0 favorites 0 likes
#software-agents

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Hugging Face Daily Papers ↗ · 2026-07-16 Cached

RESOURCE2SKILL is a framework that distills executable agent skills from multimodal resources like tutorial videos, code repositories, articles, and artifacts into a hierarchical SkillWiki, improving agent performance by 11.9 percentage points over no-skill agents.

0 favorites 0 likes
← Back to home

Submit Feedback