跳到正文
Jones Ray

ScholarPulse 日报 2026-09-22

2026-09-22 学术简报:2 篇。论文提出 HAAC,面向生成式 AI 审计的人机协作工作流与系统,让 AI 代理支持探索、评估、报告与审查,并保留人类关键判断。

今日速览

序号标题来源日期主题推荐等级
1Who Does What in AI Auditing? Designing Human-AI Collaboration for Auditing Generative AIarXiv2026-09-21RAG高
2RRSI: Regularized Recursive Self-Improvement of Agent HarnessesarXiv2026-09-21RAG高

重点论文与技术动态

1. Who Does What in AI Auditing? Designing Human-AI Collaboration for Auditing Generative AI

一句话结论

论文提出 HAAC,面向生成式 AI 审计的人机协作工作流与系统,让 AI 代理支持探索、评估、报告与审查,并保留人类关键判断。

核心内容

方法与数据

价值判断

摘要 AI auditing increasingly incorporates AI agents to expand the scale and breadth of audit coverage, yet little is known about how auditing work should be divided without displacing human judgment. We introduce Human-Agent Audit Collaboration (HAAC), a workflow and system for structuring human-AI collaboration in AI auditing. Drawing on prior work and formative consultations with AI auditing practitioners, HAAC specifies how agents can support exploration, assessment, reporting, and review while preserving human oversight where contextual judgment is critical. We instantiate HAAC for conversational shopping agents and evaluate it through two studies. With 71 auditors, AI assistance increased attack success and broadened exploration, while also shaping later attacks and increasing auditors' reliance on AI-generated assessments and reports. Interviews with Responsible AI practitioners showed that actionable audits require visibility into coverage, reproducible attack trajectories, and evaluation of the auditing agents themselves. Our findings identify design considerations for effective and accountable human-AI auditing.

2. RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

一句话结论

RRSI 以正则化约束智能体外壳递归自我改进,降低过拟合并提升分布外泛化。

核心内容

方法与数据

价值判断

摘要 An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically establishing a form of recursive self-improvement (RSI) at the agent-system level. However, such recursive evolution may overfit by memorizing the training tasks, showing large in-distribution gains that shrink or even vanish on out-of-distribution benchmarks. We introduce Regularized Recursive Self-Improvement of Agent Harnesses (RRSI), which incorporates the principles of regularizations into harness self-improvement by constraining the evolution candidate proposal and selection. The proposer operates with a temporally annealed budget, limiting how many edits a candidate can bundle, and it encourages unexplored trajectories based on evolution history. The selector is equipped with a critic and a pruner: the critic screens benchmark-specific proposals, while the pruner, removes changes that are too small, too expensive, or no longer useful. Together these constraints favor reusable agent mechanisms over benchmark-specific ones or even noises. Across eight benchmarks spanning coding, agentic workspace and engineering design tasks, RRSI gains up to 14.1 points on the split it evolves against and up to 4.7 points on the five out-of-distribution benchmarks, while producing a harness that runs on 30% fewer policy tokens than the unregularized evolution. Code is available at https://github.com/google-research/rrsi and project page is https://regularized-rsi.com/.