arXiv:2605.06136v1 Announce Type: cross Abstract: Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it as working context. In that setting, a generated repository is not only an answer to a task but also […]
Autoregressive Visual Generation Needs a Prologue
arXiv:2605.06137v1 Announce Type: cross Abstract: In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a small set of prologue tokens prepended to the visual token sequence. These prologue tokens are trained exclusively with […]
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
arXiv:2605.05097v2 Announce Type: replace-cross Abstract: LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let […]
Modularity Emerges from Action-Functional Constraints in Marine Metabolic Networks: A Biology-Scale Validation of the Network-Weighted Action Principle
arXiv:2605.05254v1 Announce Type: new Abstract: Biological systems operate under simultaneous energetic and informational constraints, yet direct evidence that such constraints shape real metabolic networks is limited. The Network-Weighted Action Principle predicts that networks under these constraints should organize toward high modularity. We tested this prediction in marine microbiome metabolic networks reconstructed from Tara Oceans metagenomes […]
A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization
arXiv:2605.06226v1 Announce Type: new Abstract: Accurate and timely diagnosis is essential for effective treatment, particularly in the context of rare diseases. However, current diagnostic workflows often lead to prolonged assessment times and low accuracy. To address these limitations, we introduce Hygieia, a multi-modal AI agent system designed to support precision disease diagnosis by integrating diverse […]
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
arXiv:2605.06127v1 Announce Type: cross Abstract: Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local corruption patterns without test-time degradation labels. Existing methods typically modulate a shared backbone with global prompts or degradation descriptors, or route features through predefined expert pools. […]
A Regime Theory of Controller Class Selection for LLM Action Decisions
arXiv:2605.06339v1 Announce Type: new Abstract: Deployed language and vision-language models must decide, on each input, whether to answer directly, retrieve evidence, defer to a stronger model, or abstain. Contrary to the common monotonicity intuition, greater per-input expressivity is not uniformly beneficial in finite samples: under identical strict cross-validation, different benchmarks prefer different controller classes. This […]
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
arXiv:2605.03213v2 Announce Type: replace-cross Abstract: Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate sensitive context, hold credentials, and operate across pipelines no single party […]
AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD
arXiv:2605.05826v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated notable success in enhancing the reasoning performance of large language models (LLMs). However, recent studies reveal that while current RLVR methods improve sampling efficiency towards correct paths, they do not elicit fundamentally new reasoning patterns. Instead, the reasoning capability boundary of trained […]
Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking
arXiv:2605.06112v1 Announce Type: cross Abstract: Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness changes, providing high dynamic range and high temporal resolution. However, existing event-based trackers often neglect the intrinsic spatial sparsity and temporal […]
Agentic, Context-Aware Risk Intelligence in the Internet of Value
arXiv:2605.05878v1 Announce Type: new Abstract: The Internet of Value (IoV) is a heterogeneous, partially-trusted network in which the dominant marginal risk is composite (route, sentiment, liquidity, and the policy a system is willing to commit to) rather than a property of any single chain. We argue that a risk primitive adequate for this regime is […]
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
arXiv:2605.05938v1 Announce Type: new Abstract: Although Multimodal Large Language Models (MLLMs) have achieved remarkable progress across many domains, their training on large-scale multimodal datasets raises serious privacy concerns, making effective machine unlearning increasingly necessary. However, existing benchmarks mainly focus on static or short-sequence settings, offering limited support for evaluating continual privacy deletion requests in realistic […]