agent/papers/items/2026-2605-11882-on-policy-self-evolution-via-failure-trajectories-for-agentic-safety-alignment.md

Paper: On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment

---

type: paper title: On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment authors: Bo Yin, Qi Li, Xinchao Wang year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.11882 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-12 updated_at: 2026-05-12 status: queued relevance: high topics:

• agent-safety
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 15 collection_queries: agent-safety

One-line Takeaway

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

Why Collected

• matched queries: agent-safety
• inferred topics: agent-safety, reasoning, tool-use
• arXiv categories: cs.AI
• collection score: 15

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/2605.11882