agent/papers/items/2026-2602-16931-narrow-fine-tuning-erodes-safety-alignment-in-vision-language-agents.md

Paper: Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents

---

type: paper title: Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents authors: Idhant Gulati, Shivam Raval year: 2026 venue: arXiv url: https://arxiv.org/abs/2602.16931 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-02-18 updated_at: 2026-03-15 status: queued relevance: high topics:

• agent-evaluation
• agent-safety methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: language-agent

One-line Takeaway

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

Why Collected

• matched queries: language-agent
• inferred topics: agent-evaluation, agent-safety
• arXiv categories: cs.AI
• collection score: 14

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/2602.16931