Fine-grained visual reasoning is essential for remote sensing in urban management, yet remains underexplored in the evaluation of multimodal large language models (MLLMs). We introduce UMBench, a fine-grained urban remote sensing benchmark built from unmanned aerial vehicle (UAV) images for multiple urban management tasks such as traffic monitoring, urban construction, environmental quality, and disaster warning. Evaluations on UMBench reveal that current MLLMs often rely on scene-level priors and overlook fine-grained visual evidence. To address this issue, we further propose a novel evidence-first chain-of-thought method that directs models to inspect fine-grained visual evidence in a training-free manner. Experiments show that our method can improve the performance of both open-source and commercial MLLMs on UMBench.
Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the ambient motion that makes environments immersive. We present AniGS, a method for scene-level animation of 3D Gaussian Splatting (3DGS) reconstructions that adds subtle, distributed dynamics, e.g., vegetation motion, while preserving rigid structures. Unlike existing 3D animation techniques which are limited to object-centric subjects or small regions, AniGS is designed for large, cluttered, navigable scenes. AniGS represents the scene with a canonical 3DGS and models motion using a time-conditioned deformation field. To animate the entire scene, we leverage a pretrained video diffusion model and introduce an iterative dataset--model update strategy that progressively expands viewpoint coverage and repeatedly updates camera-fixed training videos using a render-and-refine scheme. To prevent artifacts from unintended motion in static areas, we further introduce a composed video-to-video refinement scheme that restricts motion to desired regions. Experiments on five real-world, large-scale outdoor scenes demonstrate that AniGS produces natural ambient dynamics and high-quality novel view videos, enabling more immersive viewing experiences of reconstructed environments.
The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more ``human''. We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the same prompts, we show that repeated paraphrasing moves the machine distribution toward a human target under mixing and stability conditions. We derive an explicit convergence rate, examine how semantic-preservation and quality constraints affect this rate, and extend the analysis to finite samples to characterize how the required human data and paraphrasing rounds scale with the desired error. We extend the analysis beyond the shared-parameter setting by learning a human-preserving rewriting kernel.
An agent acting in a stateful environment can leave evidence of harm in two places: the record of what it did and said, or the world it changed. Safety evaluations for discovering harm examine one or the other in limited ways, using either an LLM judge over the trajectory or deterministic checks over the final state. Although LLM-based verifiers that inspect the environment exist, they have been used to verify task completion, not to detect and confirm harm in a safety setting. We address this gap with an LLM that has read-only access to the environment state and is given a harm taxonomy. We evaluate this approach in three environments: two from DecodingTrust-Arena and one from OSWorld. We hold the judge model and harm taxonomy fixed, varying only what the judge observes: the trajectory, read-only tools for inspecting the environment, or both channels together. In the two DecodingTrust-Arena environments, combining the trajectory and state-only judges recalls 94 percent of confirmed harms, compared with 53 percent for the trajectory judge alone. On OS-Harm, the union recalls 77 percent, compared with 67 percent. A single judge given both channels does not perform better and produces more false negatives than the state-only judge. We also record disagreements and find that the two channels miss different episodes. These results suggest that combining verdicts from two channel-specific judges is a robust and flexible approach to detecting and verifying harm in agentic settings.
LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to detect such collusions can be fooled by obfuscation and steganography, motivating the use of probes trained on internal activations. However, these probes are usually evaluated on agents that do not know they are being watched. We study how activation-based detection changes when agents are explicitly informed that their internal activations are being monitored, and when they additionally receive feedback from the monitor. We keep the models, probes, and thresholds fixed and change only what the agents are told: nothing (baseline), that an activation monitor is present (aware), or that a monitor is present together with the previous round's score (feedback). We test two games, a four-agent blackjack game and a two-agent Simmons prisoners game, using Qwen3-32B-AWQ and GPT-OSS-20B in homogeneous and mixed pairings. Telling agents about the monitor does not hide them. The best probes stay accurate in all three conditions, and the agents keep colluding.
Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge. We present DualGauge, the first fully automated framework for jointly evaluating correctness and security of specification-only code generation, supported by DualGauge-Bench, a language-agnostic benchmark of 307 coding tasks each paired with functional and security tests derived from the same specification. Evaluating 10 representative LLMs across Python, C++, and JavaScript, we find that functional correctness substantially overestimates reliable code generation: even the strongest model remains below 15% joint security-functionality success in every language. Common model-side factors--scale, extended thinking, quantization, instruction tuning, and code specialization--do not reliably improve joint performance, suggesting secure-and-correct code generation does not simply emerge from stronger coding capability. Evaluation of 3 leading coding agents (Codex, OpenHands, and Claude Code) shows that iterative scaffolding is not a reliable remedy on specification-only tasks: results are strongly scaffold-dependent, with two of the three agents failing to outperform a comparable direct model. A qualitative audit reveals that these failures concentrate at the output contract boundary and in guards that exist but are insufficient--patterns that only joint benchmarking reliably exposes.
Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan 等 11 位作者
原文摘要
Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. This execution model exposes agents to indirect prompt injection (IPI) attacks, in which attacker-controlled instructions embedded in external artifacts enter the agent state and later influence tool use. Multi-turn IPI is especially challenging because injected content can persist across steps and trigger unauthorized state-changing actions only after merging with user intent. This creates a source-attribution problem: existing inference-time defenses can often detect suspicious behavior but do not directly distinguish whether a pending action is supported by the user task or influenced by injected content. They therefore resort to conservative blocking, termination, or broad filtering. We propose AgentSentry, an inference-time defense that operationalizes temporal causal diagnostics through boundary-local counterfactual re-executions at tool-return boundaries. It substitutes the mediator under a restored snapshot, records whether the pending proposal survives, and aggregates user-view and probe scores across adjacent boundaries. When a proposal is mediator-sensitive, AgentSentry purifies the implicated mediator content while preserving task-relevant evidence and resumes execution from the sanitized state. We evaluate AgentSentry on AgentDojo across four task suites, three IPI attack families, and three black-box LLM backbones. It records no observed successful attack in the evaluated cases (ASR = 0%) and achieves an average Utility Under Attack (UA) of 76.10%. Over the strongest evaluated baseline, it improves average UA by 1.84--7.60 percentage points, with benign FPRs of 2.06%--5.15%. We further evaluate long-horizon and adaptive attacks, imperfect purification, runtime overhead, and an OpenClaw case study.