arXiv:2609.38291v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtim...
SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to improve safety alignment for LLM‑based agents. It uses on‑policy trajectory safety evidence to update safety prompts and hierarchical skills, producing auditable harness artifacts. The policy is trained via a two‑stage SFT‑RL pipeline that bootstraps with the evolved harness and then refines behavior through verifier‑decomposed rewards, yielding a better safety‑utility tradeoff on benchmarks such as AgentDojo.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to align large‑language‑model agents with safety goals. It uses completed on‑policy trajectories to update safety prompts and hierarchical skills, then applies a two‑stage SFT‑RL training loop that bootstraps the policy with the evolved harness and refines it through verifier‑augmented rewards. Experiments on agentic safety benchmarks show that SafeEvolve improves the safety‑utility tradeoff, achieving a three‑fold reduction in ASR on AgentDojo for Qwen3.5‑4B while increasing benign utility from 59.79% to 61.86%.
arXiv:2608.00677v2 Announce Type: replace Abstract: AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-mo...
arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their con...
arXiv:2608. 12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state.
HarnessRisk is a lifecycle-oriented benchmark for evaluating safety in agent harnesses that manage tools, extensions, state, permissions, and external actions. It defines six operational phases—Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery—and includes 128 sandboxed cases pairing benign user objectives with adversarial instructions. Across three harnesses, six language models, and 14 configurations, attack success rates vary from 12.6% to 80.9%, with the most vulnerable phase being Harness Configuration. "whyItMatters":"The benchmark demonstrates that safety failures can arise in multiple harness responsibilities and that even explicit risk detection does not guarantee safe action, underscoring the need for comprehensive evaluation across model and harness configurations."
SEABench is a benchmark designed to study endogenous misalignment in self‑evolving large language model agents. It contains 48 longitudinal task sequences across various evolution surfaces, task domains, and harm types, and includes an adaptive trajectory discovery pipeline that probes for failures while preserving task intent. Evaluations show that self‑evolution improves task completion rates but often introduces safety failures absent in non‑evolving baselines, with divergent safety behaviors reflected in agents’ chain‑of‑thought reasoning that can be monitored to mitigate unsafe actions.
arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.
arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.
SafeCoEvo is a test‑time framework that co‑evolves safety harnesses and guards for large language model agents. It uses a short‑term S‑Harness to quickly externalize recent runtime experience into explicit safety knowledge, and a long‑term GuardVPO to internalize accumulated experience into parametric risk‑judgment capabilities. This dual adaptation improves safety and task success, reducing unsafe outcomes by 10.05% and increasing task success by 12.15% over the strongest baseline.