Daily Papers

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels of agent and monitor situational awareness; (2) distinct adversarial strategies to evade the monitor, such as prompt injection; and (3) two datasets and environments -- SHADE-Arena for tool-calling agents and our new CUA-SHADE-Arena, which extends TheAgentCompany, for computer-use agents. We run MRT on existing LLM monitor scaffoldings, which orchestrate LLMs and parse agent trajectories, alongside a new hybrid hierarchical-sequential scaffolding proposed in this work. Our empirical results yield three key findings. First, agent awareness dominates monitor awareness: an agent's knowledge that it is being monitored substantially degrades the monitor's reliability. On the contrary, providing the monitor with more information about the agent is less helpful than expected. Second, monitor scaffolding matters more than monitor awareness: the hybrid scaffolding consistently outperforms baseline monitor scaffolding, and can enable weaker models to reliably monitor stronger agents -- a weak-to-strong scaling effect. Third, in a human-in-the-loop setting where humans discuss with the LLM monitor to get an updated judgment for the agent's behavior, targeted human oversight is most effective; escalating only pre-flagged cases to human reviewers improved the TPR by approximately 15% at FPR = 0.01. Our work establishes a standard workflow for MRT, highlighting the lack of adversarial robustness for LLMs and humans when monitoring and detecting agent misbehavior. We release code, data, and logs to spur further research.

Plagiarism detection is well known phenomenon in the academic arena. Copying other people is considered as serious offence that needs to be checked. There are many plagiarism detection systems such as turn-it-in that has been developed to provide this checks. Most, if not all, discard the figures and charts before checking for plagiarism. Discarding the figures and charts results in look holes that people can take advantage. That means people can plagiarized figures and charts easily without the current plagiarism systems detecting it. There are very few papers which talks about flowcharts plagiarism detection. Therefore, there is a need to develop a system that will detect plagiarism in figures and charts. This paper presents a method for detecting flow chart figure plagiarism based on shape-based image processing and multimedia retrieval. The method managed to retrieve flowcharts with ranked similarity according to different matching sets.

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

A large scale collection of both semantic and natural language resources is essential to leverage active Software Engineering research areas such as code reuse and code comprehensibility. Existing machine learning models ingest data from Open Source repositories (like GitHub projects) and forum discussions (like Stackoverflow.com), whereas, in this showcase, we took a step backward to orchestrate a corpus titled PyTorrent that contains 218,814 Python package libraries from PyPI and Anaconda environment. This is because earlier studies have shown that much of the code is redundant and Python packages from these environments are better in quality and are well-documented. PyTorrent enables users (such as data scientists, students, etc.) to build off the shelf machine learning models directly without spending months of effort on large infrastructure. The dataset, schema and a pretrained language model is available at: https://github.com/fla-sil/PyTorrent

Heatwaves pose significant health risks, particularly due to prolonged exposure to high summer temperatures. Vulnerable groups, especially pedestrians and cyclists on sun-exposed sidewalks, motivate the development of a route planning method that incorporates somatosensory temperature effects through shade ratio consideration. This paper is the first to introduce a pipeline that utilizes segmentation foundation models to extract shaded areas from high-resolution satellite images. These areas are then integrated into a multi-layered road map, enabling users to customize routes based on a balance between distance and shade exposure, thereby enhancing comfort and health during outdoor activities. Specifically, we construct a graph-based representation of the road map, where links indicate connectivity and are updated with shade ratio data for dynamic route planning. This system is already implemented online, with a video demonstration, and will be specifically adapted to assist travelers during the 2024 Olympic Games in Paris.