Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step.
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts.
Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative-Weights Update (OMWU) are two very popular algorithms to solve convex/concave saddle-point problems, where OMWU is the non-Euclidean, entropic version of OGDA. It is known since the '80s that the last iterate of OGDA asymptotically converges to a saddle point in smooth problems.
Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks.
End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode.
Problem, Research Strategy, and Findings: The rise of large language models (LLMs) raises a key question for urban planning: which forms of professional planning knowledge can AI replicate, and which still require human judgment? Although AI tools are increasingly used in planning practice, there is still no systematic framework for testing whether they can reason with the contextual sensitivity, value awareness, and institutional literacy central to planning expertise.
Accurate salary prediction is critical for bridging the information gap between employers and job seekers in modern labor markets. Existing approaches predominantly yield a single point estimate and treat job attributes such as location, occupation, and industry as independent categorical features, ignoring both the inherent uncertainty and multi-modality of real-world compensation data and the rich hierarchical and semantic-similarity relationships that govern pay norms.
Large language models often remain sensitive to answer format: a question solved correctly in one form may fail in another semantically equivalent form. To study this gap, we define cross-format robustness as the extent to which a model answers the same underlying question consistently across formats.
arXiv:2506. 09171v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient.
arXiv:2606. 10199v1 Announce Type: new Abstract: Insertion Language Models (ILMs) offer several advantages over left-to-right generation and mask-based generation.
arXiv:2606. 11033v1 Announce Type: cross Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation.
arXiv:2505. 23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization with genuine reasoning.
arXiv:2510. 12071v2 Announce Type: replace Abstract: Current training data attribution (TDA) methods treat the influence one sample has on another as static, but neural networks learn in distinct stages that exhibit changing patterns of influence.
arXiv:2606. 10392v1 Announce Type: new Abstract: Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs.
arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.
arXiv:2606. 09954v1 Announce Type: cross Abstract: Large models for time-series forecasting have been emerged as a promising paradigm for training models on heterogeneous collections of signals.
arXiv:2606. 09872v1 Announce Type: cross Abstract: Traffic forecasting is a fundamental component of intelligent transportation systems, yet remains challenging in real-world settings due to irregular sensor distributions and the high computational cost of modeling large-scale spatiotemporal dependencies.
arXiv:2606. 09837v1 Announce Type: cross Abstract: Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-speech (TTS) synthesis.
arXiv:2606. 10046v1 Announce Type: cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque.
arXiv:2603. 04852v2 Announce Type: replace Abstract: Multi-step theorem prediction is a central challenge in geometry problem solving.