跳到正文
Jones Ray

ScholarPulse 日报 2026-08-31

2026-08-31 学术简报:2 篇。安全代理需要外部强制,而非仅依赖更好的识别。

今日速览

序号标题来源日期主题推荐等级
1Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External ControlarXiv2026-08-28RAG高
2LUCID: An Agentic AI Framework on Digital-Twin in the Loop for QoS-Guaranteeing Robotic ControlarXiv2026-08-28AI-Agent高

重点论文与技术动态

1. Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control

一句话结论

安全代理需要外部强制,而非仅依赖更好的识别。

一段话:LLM代理在指令仲裁中存在识别-执行差距,模型能解码源格式特征(如角色模板位置、通道元数据)并识别伪造权威,但特定配置仍导致冲突工具调用;漏洞集中在可重现单元,随部署窗口动态变化(窗口内最高47个百分点);外部参考监控通过认证源路由与能力门控工具执行,确定性拒绝所有测试的伪造、篡改、重放及未签名请求。

核心内容

方法与数据

价值判断

摘要 LLM agents arbitrate among instructions from system prompts, users, memory, and tools, but this arbitration cannot be assumed to enforce trust boundaries. We identify a recognition-enforcement gap: source-format features (role-template position, channel metadata, formatting cues) are linearly decodable from model activations, and models can explicitly identify forged authority when prompted, yet some configurations still produce the conflicting tool call. We use "recognition" in this specific decodable-source-format-plus-verbalized-detection sense; crossed-probe controls show it is not a unified abstract trust representation. The gap is not an immutable property of model weights. Restrictive policies and diverse prompts can eliminate execution on the same models, while permissive configurations and particular prompt-model pairs yield deterministic failures. Across a fleet evaluation (authority spoofing: 46 model endpoints across 6 vendors including open-weight; memory conflict: 48 models), average execution under diverse novel attacks is 1.21% [0.5-2.1%] (model-clustered CI over 14,294 spoofed trials from 29 models), but vulnerability is concentrated in reproducible cells and shifts across deployment windows (up to 47pp within-window per-fingerprint range). Prompt-layer defenses likewise fail to generalize across models and adaptive formulations. We therefore treat model self-arbitration as a capability rather than a security boundary and implement an external reference monitor combining authenticated source routing with capability-gated tool execution. It deterministically rejects all tested forged, tampered, replayed, and unsigned requests while preserving legitimate operations. A separate adaptive red-team found one implementation flaw (a since-patched clock-skew admission), not a cryptographic bypass. Secure agents require external enforcement, not merely better recognition.

2. LUCID: An Agentic AI Framework on Digital-Twin in the Loop for QoS-Guaranteeing Robotic Control

一句话结论

LUCID通过动态协调轨迹规划与无线资源管理,实现云机器人系统在动态环境中的QoS保障。

一段话:LUCID将轨迹规划和无线资源管理从固定优化问题转变为动态配置的优化问题模式,由操作员高级意图驱动;利用SimBridge将大规模机器人场景转换为无线就绪数字孪生,实现高效无线冲突评估;并通过FastConfigNet降低规划延迟,实验验证其在变化意图、机器人数量和场景中的稳健适应性。

核心内容

方法与数据

价值判断

摘要 Cloud robotics relies on the timely uplink of high-volume sensing streams, yet dynamic environments continually shift the feasible combinations of trajectories, active-robot count, and per-robot QoS. Because existing approaches formulate trajectory planning (TP) and radio resource management (RRM) as a single fixed optimization problem, they cannot reconfigure these coupled decisions as conditions evolve, resulting in transient QoS violations. However, evolving operator intents change which quantities-such as the active-robot count and per-robot QoS-are fixed, optimized, or relaxed. Furthermore, the computational cost of evaluating trajectory-dependent wireless conflicts has made it difficult to build large-scale Digital-Twin-in-the-Loop (DITL) testbeds responsive enough for such dynamic orchestration. We present LUCID, an LLM-agent--orchestrated, uplink-aware cloud-robotics pipeline that moves TP--RRM from solving a fixed formulation to dynamically orchestrating optimization problem schemas within a DITL environment. Driven by the operator's high-level intent, LUCID treats the TP--RRM formulation as a bounded template whose variables, objectives, and constraints are dynamically configured, while SimBridge enables repeated ray-tracing evaluation by converting large-scale robotics scenes into wireless-ready DTs. By integrating collision-free path planning with a spectral-radius RRM validator, LUCID identifies wireless bottlenecks and restructures the problem schema on the fly to efficiently find the verified feasible state. Experiments confirm that LUCID robustly adapts to changing intents, active-robot counts, and scenes, while a multimodal surrogate model, FastConfigNet, reduces planning latency.