arXiv:2603.21563v2 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignment layer that converts team-level […]
DDGAD: Trajectory Dynamics for Diffusion-Based Graph Anomaly Detection
arXiv:2605.26446v1 Announce Type: cross Abstract: Graph anomaly detection (GAD) aims to identify nodes or substructures whose behavior or attributes deviate significantly from the overall pattern in graph-structured data, with critical applications in financial risk control, social network analysis, and cybersecurity. However, existing GCN-based methods suffer from the fundamental problem of contamination propagation, where anomalous nodes […]
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
arXiv:2605.26494v1 Announce Type: new Abstract: We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven […]
Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
arXiv:2605.26463v1 Announce Type: cross Abstract: Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and clinical decision-making. However, existing work on note-table consistency verification mainly relies on surface-level matching of numeric values or simple events. Such approaches fail to capture the reasoning underlying real-world EHR […]
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
arXiv:2605.17036v3 Announce Type: replace Abstract: This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We identify four inference-time levers that shape performance: model selection, policies and guardrails, centralized data sharing, and prompt engineering. Model capability is the dominant factor: an out-of-the-box reasoning model exceeds human-level performance, and optimized […]
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
arXiv:2605.26492v1 Announce Type: cross Abstract: LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five prompts. We find that 11 words occur in 88.3% of generated stories, with little difference between models. These words include names (Elias, Mara, Elara), settings (lighthouses), […]
Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning
arXiv:2605.26530v1 Announce Type: new Abstract: Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations, but should change when perturbations alter legally material points. We formulate this requirement as a legal-relevance-sensitive evaluation problem: LLMs should only be sensitive to the legally relevant change. We […]
CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer’s Disease Pathologies
arXiv:2605.26514v1 Announce Type: cross Abstract: Confirming Alzheimer’s disease (AD) typically relies on positron emission tomography (PET), which remains costly and invasive, motivating the use of structural MRI-based prescreening. Deep learning on non-Euclidean manifolds, particularly brain cortical surfaces, faces significant challenges due to the data’s spherical topology. Recent surface models have enabled learning from cortical surface […]
Credit Assignment with Resets in Language Model Reasoning
arXiv:2605.25507v2 Announce Type: replace Abstract: Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignment ignores which steps contributed to success or failure. Improving credit assignment can address this limitation by enabling targeted refinement of faulty […]
ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation
arXiv:2605.26525v1 Announce Type: cross Abstract: Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challenge: single-shot extrapolation preserves an anchor but lacks cinematic structure, while multi-shot storytelling imposes structure yet remains free to invent its visual states rather than continue an observed one. We define […]
PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design
arXiv:2605.26543v1 Announce Type: new Abstract: Polymer discovery is central to fields ranging from energy storage to biomedicine, but it is hindered by an astronomically large chemical design space and fragmented representations of structure, properties, and prior knowledge. This fragmentation leaves many AI models disconnected from physical and experimental reality, restricting their ability to support directly […]
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
arXiv:2605.26542v1 Announce Type: cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool composition: an agent can satisfy every per-tool permission check and still produce an unsafe end-to-end effect, such as reading a confidential […]