agent/papers/items/2026-2605-28617-lacuna-safe-agents-as-recursive-program-holes.md

Paper: LACUNA: Safe Agents as Recursive Program Holes

---

type: paper title: "LACUNA: Safe Agents as Recursive Program Holes" authors: Yaoyu Zhao, Yichen Xu, Oliver Bračevac, Cao Nguyen Pham, Frank Zhengqing Wu, Martin Odersky year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.28617 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-27 updated_at: 2026-05-27 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• planning
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI
• cs.PL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 13 collection_queries: planning-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: planning-agent
• inferred topics: agent-evaluation, agent-safety, planning, rag, tool-use
• arXiv categories: cs.AI, cs.PL
• collection score: 13

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2605.28617