arXiv:2512.09566v3 Announce Type: replace Abstract: Drug discovery is a time-consuming and expensive process, with traditional high-throughput and docking-based virtual screening hampered by low success rates and limited scalability. Recent advances in generative modelling, including autoregressive, diffusion, and flow-based approaches, have enabled de novo ligand design beyond the limits of enumerative screening. Yet these models often […]
Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
arXiv:2603.10588v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the apparent tolerance for multiple valid responses in moral reasoning, a natural hypothesis is that alignment tasks inherently require diversity-seeking distribution-matching algorithms […]
Explainability of Text Processing and Retrieval Methods: A Survey
arXiv:2212.07126v3 Announce Type: replace-cross Abstract: Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview […]
Trajectory-Informed Memory Generation for Self-Improving Agent Systems
arXiv:2603.10600v1 Announce Type: new Abstract: LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically […]
Self-Improving Loops for Visual Robotic Planning
arXiv:2506.06658v3 Announce Type: replace-cross Abstract: Video generative models trained on expert demonstrations have been utilized as performant text-conditioned visual planners for solving robotic tasks. However, generalization to unseen tasks remains a challenge. Whereas improved generalization may be facilitated by leveraging learned prior knowledge from additional pre-collected offline data sources, such as web-scale video datasets, in […]
FAME: Formal Abstract Minimal Explanation for Neural Networks
arXiv:2603.10661v1 Announce Type: new Abstract: We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural networks while reducing explanation size. Our main contribution is the design of dedicated perturbation domains that eliminate the need for traversal order. FAME […]
DeepEyesV2: Toward Agentic Multimodal Model
arXiv:2511.05271v4 Announce Type: replace-cross Abstract: Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate these operations into reasoning. In this work, we introduce DeepEyesV2 and explore how to build an agentic multimodal model from the perspectives of data […]
ATP Level and Phosphorylation Free Energy Regulate Trigger-Wave Speed and Critical Nucleus Size in Cellular Biochemical Systems
arXiv:2603.10669v1 Announce Type: new Abstract: Trigger waves are self-regenerating propagating fronts that emerge from the coupling of nonlinear reaction kinetics and diffusion. In cells, trigger waves coordinate large-scale processes such as mitotic entry and stress responses. Although the roles of circuit topology and feedback architecture in generating bistability are well established, how nonequilibrium energetic driving […]
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
arXiv:2601.10955v2 Announce Type: replace-cross Abstract: The agent–tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-prompt or retrieval-augmented generation (RAG) context layer and are inherently single-turn in nature. This limitation restricts cost amplification and diminishes stealth in goal-oriented workflows. To address […]
Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
arXiv:2603.10677v1 Announce Type: new Abstract: Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges […]
Solving adversarial examples requires solving exponential misalignment
arXiv:2603.03507v2 Announce Type: replace-cross Abstract: Adversarial attacks – input perturbations imperceptible to humans that fool neural networks – remain both a persistent failure mode in machine learning, and a phenomenon with mysterious origins. To shed light, we define and analyze a network’s perceptual manifold (PM) for a class concept as the space of all inputs […]
Nurture-First Agent Development: Building Domain-Expert AI Agents Through Conversational Knowledge Crystallization
arXiv:2603.10808v1 Announce Type: new Abstract: The emergence of large language model (LLM)-based agent frameworks has shifted the primary challenge in building domain-expert AI agents from raw capability to effective encoding of domain expertise. Two dominant paradigms — code-first development, which embeds expertise in deterministic pipelines, and prompt-first development, which captures expertise in static system prompts […]