ProToMEx: Rapid, Interpretable Explanations via Structured Representations
arXiv:2609.04265v1 Announce Type: new
Abstract: Existing post-hoc explainers for machine learning classifiers primarily focus on feature attribution, assigning importance scores to individual features. While valuable, this approach struggles to articulate the complex, combinatorial patterns that of...
Quantum-Assisted Memory-Efficient Training for Parameter-Intensive Wi-Fi-Based Human Activity Recognition
arXiv:2609.04271v1 Announce Type: new
Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of context-aware services. However, most existing Wi-Fi-based HAR systems rely on deep learning (DL) models ...
arXiv:2609.04239v1 Announce Type: new
Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series (TS) foundation model (TSFM) tailored to financial forecasting. Recent TSFMs achieve strong zero-shot performance through large-scale pretraining. How...
Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning
arXiv:2609.04272v1 Announce Type: new
Abstract: This study examines the ability of large language models (LLMs) to predict the risk of weather-related forced outages in the distribution grid in a zero-shot framework, without labeled training data. The problem is formulated as a binary severity clas...
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
arXiv:2609.04298v1 Announce Type: new
Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work mak...
arXiv:2609.04304v1 Announce Type: new
Abstract: We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse-constructed from the hyperlink structure of a web corpus: we author mu...
6 reasons AI engineers can make the jump to robotics right now
Somewhere between 2,000 and a few thousand engineers in the US can genuinely combine vision-language-action models, sensor fusion, and kinematics. Against that tiny bench, the market is posting more than 65,000 open robotics roles, according to a widely cited analysis from Fruition Group.
Everyone's optimizing content for AI visibility. New research shows the cost
Generative Engine Optimization promises AI visibility, but new research shows what happens once an entire market chases the same AI ranking signal round after round. The link between winning and being genuinely good comes apart gradually, even while quality itself holds steady...
A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant
arXiv:2609.03402v1 Announce Type: new
Abstract: Artificial intelligence (AI) teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization. This study presents a prompt-engineering-based framework for personalizing general-p...
Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory
arXiv:2609.03340v1 Announce Type: new
Abstract: Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner may derive an action from requirement $r_3$, another agent may commit $r_4$, and an executor may receive $r_4$ without replacing the plan derived...
Speculative Macro Commit for Faster Tool-Using Agents
arXiv:2609.03236v1 Announce Type: new
Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment transition, and observation can delay subsequent decisions. We introduce \textbf{Speculative Macro ...
arXiv:2609.03209v1 Announce Type: new
Abstract: We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can rem...
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
arXiv:2609.02984v1 Announce Type: new
Abstract: The conventional approach to machine learning, that is, collecting data, training models, and performing inference in a single location, faces fundamental limitations, including scalability and privacy, that restrict its applicability. To address thes...
Equation Recast for Canonical Operator Learning Across Parametric PDEs
arXiv:2609.02982v1 Announce Type: new
Abstract: Learning solution operators across broad parameter ranges can require substantial coverage of both input functions and physical parameters, particularly for purely data-driven parametric models. In addition, the resulting models may fail silently outs...
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
arXiv:2609.02959v1 Announce Type: new
Abstract: What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix encodes the unigram distribution of the training corpus, which serves as the Bayesian prior the model ...
Induction and Inquiry via Probabilistic Reasoning over Language and Code
arXiv:2609.01815v1 Announce Type: new
Abstract: How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and c...
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
arXiv:2609.01608v1 Announce Type: new
Abstract: Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error r...
Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result
arXiv:2609.01615v1 Announce Type: new
Abstract: Personalizing a frozen large language model (LLM) to individual users is often framed as a meta-learning problem in prompt space: each user is a task, and one seeks a shared natural-language adaptation policy that, given a handful of the user's labele...
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
arXiv:2609.01611v1 Announce Type: new
Abstract: Frontier large language models can often recognize when they are being evaluated, a capability known as evaluation awareness. If models behave differently in evaluations than in deployment, this undermines the validity of evaluation results, which are...
CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction
arXiv:2609.01673v1 Announce Type: new
Abstract: Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve the underlying mechanisms remain limited. To use available activity labels more effectively, we combin...
When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium Selection
arXiv:2609.01814v1 Announce Type: new
Abstract: Information sharing can improve a pooled estimate while eliminating independent rescue actions. This paper separates those effects in exact finite discovery models. A centralized action-budget profile shows that equal one-person accuracy can coexist w...