arXiv:2510.26037v1 Announce Type: cross Abstract: The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring their safe deployment. We present SIRAJ: a generic red-teaming framework for arbitrary black-box LLM agents. We employ a dynamic two-step process that starts […]
Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism
arXiv:2508.15030v3 Announce Type: replace Abstract: We propose Collab-REC, a multi-agent framework designed to counteract popularity bias and enhance diversity in tourism recommendations. In our setting, three LLM-based agents — Personalization, Popularity, and Sustainability generate city suggestions from complementary perspectives. A non-LLM moderator then merges and refines these proposals via multi-round negotiation, ensuring each agent’s viewpoint […]
Dynamic VLM-Guided Negative Prompting for Diffusion Models
arXiv:2510.26052v1 Announce Type: cross Abstract: We propose a novel approach for dynamic negative prompting in diffusion models that leverages Vision-Language Models (VLMs) to adaptively generate negative prompts during the denoising process. Unlike traditional Negative Prompting methods that use fixed negative prompts, our method generates intermediate image predictions at specific denoising steps and queries a VLM […]
The FM Agent
arXiv:2510.26144v1 Announce Type: new Abstract: Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic combination of LLM-based reasoning and large-scale evolutionary search to address complex real-world challenges. The core of FM Agent […]
Learning Geometry: A Framework for Building Adaptive Manifold Models through Metric Optimization
arXiv:2510.26068v1 Announce Type: cross Abstract: This paper proposes a novel paradigm for machine learning that moves beyond traditional parameter optimization. Unlike conventional approaches that search for optimal parameters within a fixed geometric space, our core idea is to treat the model itself as a malleable geometric entity. Specifically, we optimize the metric tensor field on […]
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
arXiv:2510.19771v2 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously. However, evaluating proactivity is challenging; current benchmarks are constrained to localized context, limiting their ability to test reasoning across sources and longer time horizons. To address this gap, […]
Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
arXiv:2510.26089v1 Announce Type: cross Abstract: Traffic congestion in urban road networks leads to longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal for a single vehicle in a static network, it performs poorly in dynamic, multi-vehicle settings, often worsening congestion by routing all vehicles along […]
One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning
arXiv:2510.26167v1 Announce Type: new Abstract: Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed for function-calling tasks has limited progress toward more capable agentic AI. We introduce ToolRM, a family of lightweight generative RMs tailored […]
Security Risk of Misalignment between Text and Image in Multi-modal Model
arXiv:2510.26105v1 Announce Type: cross Abstract: Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the alignment between textual and Image modalities in existing diffusion models is inadequate. This misalignment presents significant risks, especially in the generation […]
Chaos-based reinforcement learning with TD3
arXiv:2405.09086v2 Announce Type: replace-cross Abstract: Chaos-based reinforcement learning (CBRL) is a method in which the agent’s internal chaotic dynamics drives exploration. However, the learning algorithms in CBRL have not been thoroughly developed in previous studies, nor have they incorporated recent advances in reinforcement learning. This study introduced Twin Delayed Deep Deterministic Policy Gradients (TD3), which […]