@inproceedings{bin-etal-2026-safety,
    title = "Safety Sidecar: Reflection-Driven Runtime Control for Safer Agents",
    author = "Bin, Wang  and
      Jiazheng, Quan  and
      Yu, Xingrui  and
      Hansen, Hu  and
      Hao, Yu  and
      Gao, Anjun  and
      Wan, Zhenglin  and
      LI, Hui  and
      Tsang, Ivor",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1542/",
    pages = "30842--30856",
    ISBN = "979-8-89176-395-1",
    abstract = "Autonomous LLM agents are increasingly deployed in complex environments as tool-using systems. However, their safety remains fragile, as minor reasoning or retrieval errors can be amplified into hazardous actions within the agentic workflow. Existing defenses, often limited to static prompts or post-hoc guardrails, fail to provide runtime intervention or cross-architecture portability. In this paper, we propose \textbf{Safety Sidecar}, a model-agnostic, plug-and-play module designed to provide standardized runtime safety control and auditability for arbitrary agent workflows. Safety Sidecar operationalizes reflection as a closed-loop controller: it dynamically monitors decision traces, retrieves evidence-based repair exemplars from a reflective memory, and enforces risk-mitigating revisions before execution. Crucially, it employs external verifiers to gate both action release and memory updates, producing a transparent, auditable trail of retrieved evidence and applied constraints.We instantiate and systematically evaluate Safety Sidecar in secure code generation{---}a high-stakes domain with objective vulnerability signals. Experimental results across eight CWE scenarios and four representative LLMs demonstrate that Safety Sidecar consistently improves the secure-solution rate by 2.9{--}11.2 percentage points while maintaining competitive functional correctness. Efficiency analysis shows the framework is practical for deployment, with reflection adding only 3.2s to end-to-end latency and a negligible average cost of $5.37 \times 10^{-4}$ per scenario. Our findings position Safety Sidecar as a portable and efficient control layer for enhancing the safety, compliance, and auditability of LLM-based agents."
}