arXiv:2604.24714v1 Announce Type: cross Abstract: Understanding the structure of the brain, and how it changes with time and disease, is a core goal of structural neuroimaging. Contemporary approaches to structural brain analysis are dominated by voxel-wise, mass-univariate methods such as voxel-based morphometry (VBM). However, these techniques require images to be normalized to a standard template, […]
SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
arXiv:2509.25346v2 Announce Type: replace Abstract: Predicting cellular responses to genetic perturbations represents a fundamental challenge in systems biology, critical for advancing therapeutic discovery and virtual cell modeling. While large language models (LLMs) show promise for biological reasoning, their application to perturbation prediction remains underexplored due to challenges in adapting them to structured experimental data. We […]
MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration
arXiv:2604.23129v1 Announce Type: cross Abstract: Knowledge workers face increasing challenges in synthesizing information from multiple documents into structured conceptual understanding. This process is inherently iterative: users explore content, identify relationships between concepts, and continuously reorganize their mental models. However, current approaches offer limited support. LLM-based systems let users query information but not shape how knowledge […]
Designing escalation criteria for international AI incident response: criteria, triggers, and thresholds
arXiv:2604.23183v1 Announce Type: cross Abstract: AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper proposes an escalation framework to address this gap, intended as a common reference point across jurisdictions that enables […]
AI Identity: Standards, Gaps, and Research Directions for AI Agents
arXiv:2604.23280v1 Announce Type: new Abstract: AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify, verify, and hold accountable an entity with no body, no persistent memory, and no legal standing? We […]
UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks
arXiv:2604.23145v1 Announce Type: cross Abstract: Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task’s inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs) perform implicitly, leaving their internal decision process opaque. In contrast, large reasoning models (LRMs) explicitly generate intermediate logical steps that […]
SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
arXiv:2509.25346v2 Announce Type: replace Abstract: Predicting cellular responses to genetic perturbations represents a fundamental challenge in systems biology, critical for advancing therapeutic discovery and virtual cell modeling. While large language models (LLMs) show promise for biological reasoning, their application to perturbation prediction remains underexplored due to challenges in adapting them to structured experimental data. We […]
Designing escalation criteria for international AI incident response: criteria, triggers, and thresholds
arXiv:2604.23183v1 Announce Type: cross Abstract: AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper proposes an escalation framework to address this gap, intended as a common reference point across jurisdictions that enables […]
When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
arXiv:2604.22873v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) can learn effective policies from fixed datasets, but deployment objectives may change after training, and in many applications the trained actor cannot be retrained because of data, cost, or governance constraints. We study deployment-time adaptation for frozen offline actors using Product-of-Experts (PoE) composition with a goal-conditioned […]
Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs
arXiv:2604.22893v1 Announce Type: cross Abstract: Traditional data valuation methods based on “row-count $times$ quality coefficient” paradigms fail to capture the nuanced, nonlinear contributions that data makes to Large Language Model (LLM) capabilities. This paper presents a dynamic data valuation framework that transitions from static accounting to utility-based pricing. Our approach operates on three layers: (1) […]
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
arXiv:2604.22820v1 Announce Type: cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibility can also introduce coordination overhead and substantial inference cost. We study complete cyclic subtask graphs, a deliberately maximally flexible multi-agent architecture in which executable subtask nodes are fully connected and a unified […]
Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery
arXiv:2604.23940v1 Announce Type: cross Abstract: Decompilation — recovering source code from compiled binaries — is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or execute correctly, limiting their practical utility. We present a multi-agent framework that transforms decompiled code into re-executable source […]