arXiv:2603.15726v1 Announce Type: cross Abstract: We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage […]
Knowledge Graph Extraction from Biomedical Literature for Alkaptonuria Rare Disease
arXiv:2603.15711v1 Announce Type: new Abstract: Alkaptonuria (AKU) is an ultra-rare autosomal recessive metabolic disorder caused by mutations in the HGD (Homogentisate 1,2-Dioxygenase) gene, leading to a pathological accumulation of homogentisic acid (HGA) in body fluids and tissues. This leads to systemic manifestations, including premature spondyloarthropathy, renal and prostatic stones, and cardiovascular complications. Being ultra-rare, the […]
CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
arXiv:2603.15771v1 Announce Type: cross Abstract: Autonomous driving requires safe planning, but most learning-based planners lack explicit self-correction ability: once an unsafe action is proposed, there is no mechanism to correct it. Thus, we propose CorrectionPlanner, an autoregressive planner with self-correction that models planning as motion-token generation within a propose, evaluate, and correct loop. At each […]
Real-Time Decoding of Movement Onset and Offset for Brain-Controlled Rehabilitation Exoskeleton
arXiv:2603.16825v1 Announce Type: cross Abstract: Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling […]
Don’t Trust Stubborn Neighbors: A Security Framework for Agentic Networks
arXiv:2603.15809v1 Announce Type: cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature introduces new security risks: malicious or compromised agents can exploit communication channels to propagate misinformation and manipulate collective outcomes. In this paper, we […]
Context-Length Robustness in Question Answering Models: A Comparative Empirical Study
arXiv:2603.15723v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings where relevant information is embedded within long and noisy contexts. Despite this, robustness to growing context length remains poorly understood across different question answering tasks. In this work, we present a controlled empirical study of context-length robustness in large language models using […]
FlashSampling: Fast and Memory-Efficient Exact Sampling
arXiv:2603.15854v1 Announce Type: cross Abstract: Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that fuses sampling into the LM-head matmul and never materializes the logits tensor in HBM. The method is […]
From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation
arXiv:2509.05469v2 Announce Type: replace Abstract: Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data […]
PhasorFlow: A Python Library for Unit Circle Based Computing
arXiv:2603.15886v1 Announce Type: cross Abstract: We present PhasorFlow, an open-source Python library introducing a computational paradigm operating on the $S^1$ unit circle. Inputs are encoded as complex phasors $z = e^itheta$ on the $N$-Torus ($mathbbT^N$). As computation proceeds via unitary wave interference gates, global norm is preserved while individual components drift into $mathbbC^N$, allowing algorithms […]
CUBE: A Standard for Unifying Agent Benchmarks
arXiv:2603.15798v1 Announce Type: new Abstract: The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating an “integration tax” that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped […]
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning
arXiv:2603.15914v1 Announce Type: cross Abstract: AI tools and agents are reshaping how researchers work, from proving theorems to training neural networks. Yet for many, it remains unclear how these tools fit into everyday research practice. This paper is a practical guide to AI-assisted research in mathematics and machine learning: We discuss how researchers can use […]
Zero-Shot Time Series Foundation Models for Annual Institutional Forecasting Under Data Sparsity
arXiv:2602.12120v2 Announce Type: replace Abstract: Forecasting annual institutional demand is notoriously difficult due to data sparsity, reporting changes, and regime shifts. Traditional baselines often falter under these low signal-to-noise conditions, yet sample sizes are too small for complex parameterised models. We benchmark zero-shot Time Series Foundation Models (TSFMs) against classical persistence and ARIMA baselines for […]