arXiv:2610.03938v1 Announce Type: new
Abstract: Agentic multimodal large language models (MLLMs) have recently pushed the frontier of visual reasoning by calling tools such as zooming and tagging. Despite the recent strong success of agentic MLLMs, this work uncovers a critical safety failure in th...
SGAnalog: An End-to-End Circuit Benchmark from Open-Source Silicon Tapeouts
arXiv:2610.03934v1 Announce Type: new
Abstract: Existing analog integrated circuit design benchmarks make two questions hard to answer: whether a model has learned transferable circuit skills rather than recalled familiar examples, and whether its output works under defined process and test conditi...
Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
arXiv:2610.03894v1 Announce Type: new
Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier chat APIs hide the model's token probabilities; the agent's stated confidence barely beats chance on th...
REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers
arXiv:2610.03888v1 Announce Type: new
Abstract: Reconstructing global sea surface pH from sparse observations is critical for monitoring ocean acidification and understanding marine carbon cycling. Traditional assimilation and inverse models are physically grounded but costly for large-scale recons...
Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery
arXiv:2610.03872v1 Announce Type: new
Abstract: AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underly...
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
arXiv:2610.02330v1 Announce Type: new
Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condition subsequent decisions. In long-horizon tool use, final-outcome rewards provide weak credit assig...
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
arXiv:2610.02267v1 Announce Type: new
Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with ...
MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
arXiv:2610.02260v1 Announce Type: new
Abstract: Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers often face a trade-off...
Nearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions
arXiv:2610.02249v1 Announce Type: new
Abstract: It has recently been shown that nearest-neighbour retrieval provides a strong baseline for molecular fingerprint prediction from MS/MS spectra, with several variants matching or outperforming current deep learning models (Khoo and Barzilay, 2026; Liu ...
State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting
arXiv:2610.02248v1 Announce Type: new
Abstract: Operational land surface forecasting systems built on Mamba-family Structured State Space Models absorb non-stationary confounding events (unrecorded irrigation booms, dam-operation shifts, sensor recalibrations) into their state-transition matrices, ...
Hybrid Machine Learning-Assisted Raman Spectroscopy with Generative Feature Augmentation for Pharmaceutical Identification
arXiv:2610.02224v1 Announce Type: new
Abstract: Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical Raman-based screening. In this study, we propose HyMLRaman, a hybrid Raman spectroscopy framework th...
Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems
Designed artifacts are ontological, shaping, and at times limiting, what becomes possible or imaginable. One path toward mitigating such foreclosures is giving people power over how systems are designed and built. Despite decades of scholarship around systems that enable such authorship, these syste...
arXiv:2610.00049v1 Announce Type: new
Abstract: Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardware evolves. FlashAttention-4 exposed this imbalance inside attention on NVIDIA Blackwell. We test w...
Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System
arXiv:2610.00035v1 Announce Type: new
Abstract: Predicting student performance from educational interaction data requires models that are both accurate and sufficiently transparent to support meaningful intervention, while demographic information introduces an additional risk of unfair predictions....
EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents
arXiv:2609.38193v1 Announce Type: new
Abstract: Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires reliable histories of patient conditions, treatments, and the information available at each decision. Elec...
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
arXiv:2610.00025v1 Announce Type: new
Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-sh...
From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
arXiv:2610.00015v1 Announce Type: new
Abstract: Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We present Praxa, an agent harness that represents these states explicitly through de...
When Do Causal World Models Help Modular LLM Agents
arXiv:2610.00012v1 Announce Type: new
Abstract: LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are valid in another. Standard world models usually fit observational traces, but this ...
Heavy-Tailed Memory Traces in Long-Horizon Language Agents
arXiv:2610.00010v1 Announce Type: new
Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task success or token cost. We argue that the missing object is the shape of memory use: under finite cont...
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on...
This new qubit could be 100 times less error-prone in superfluid quantum computer breakthrough
A proposed qubit made with superfluid helium could cut quantum computing error rates by around 100 times by shielding quantum information from common forms of electromagnetic noise. If experiments confirm the predictions, the technology could eventually work alongside today’s superconducting qubits ...
This light-powered AI can spot deepfakes with nearly 98% accuracy
UCLA researchers built an AI system that uses light to analyze more than a dozen videos simultaneously, detecting deepfakes with nearly 98% accuracy. Its speed, low energy demands, and resistance to attacks could make it a powerful tool for screening the growing flood of AI-generated video.
arXiv:2609.38296v1 Announce Type: new
Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate this, we simulate conversations between two agents: a target LLM that role-plays a human persona base...