Search: “llm”

arXiv:2603.16448v3 Announce Type: replace Abstract: Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environm

arXiv:2609.10962v1 Announce Type: cross Abstract: Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, pop

arXiv:2609.11282v1 Announce Type: new Abstract: Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know wheth

arXiv:2609.10654v1 Announce Type: cross Abstract: The Abstraction and Reasoning Corpus (ARC) benchmarks cognitive generalization, the ability to infer and apply abstract rules from limited examples. T

arXiv:2609.11620v1 Announce Type: new Abstract: High-dimensional dense text embeddings and large language models face real obstacles in financial-disclosure analysis: context-window limits, hallucinat

arXiv:2609.10608v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in generative tasks across various areas, however their training process raises significant privacy

arXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), r

arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test w

arXiv:2606.20041v2 Announce Type: replace-cross Abstract: We propose an AI economist agent for economic and financial scenario analysis. Scenario design often requires analysts to assess emerging risk

arXiv:2609.10594v1 Announce Type: cross Abstract: Expert evaluation of jailbreak responses is costly and difficult to scale, so the community increasingly relies on automated evaluators to determine w

arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding th

arXiv:2609.10722v1 Announce Type: new Abstract: Structured extraction from Chinese military news supports intelligence analysis, decision-making, and knowledge base construction. However, existing res

arXiv:2609.11917v1 Announce Type: cross Abstract: As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data

arXiv:2609.09448v1 Announce Type: new Abstract: As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. I

arXiv:2609.11569v1 Announce Type: cross Abstract: We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale.

I wanted to see how my fully local home voice assistant compared to the latest GPT Live, so I tested it using the same conversation used in their 'Improved Intelligence' demo. In this video they ask t

arXiv:2603.28458v4 Announce Type: replace Abstract: Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every histori

arXiv:2609.11851v1 Announce Type: new Abstract: Language identification in code-mixed text, largely observed in social media, is highly essential when users frequently switch between multiple language

Interesting paper from Microsoft. If you run persistent memory for a production agent, this one is worth your time. (bookmark it) Memory curators usually read only the finished trajectory. That lets t

arXiv:2609.11708v1 Announce Type: new Abstract: The use of B-splines and Non-Uniform Rational B-Splines surfaces constitutes the mathematical foundation of contemporary computer-aided design (CAD) sys

arXiv:2609.10559v1 Announce Type: cross Abstract: To address the challenges of behavioral multimodality, limited semantic utilization, and long-term error accumulation in vessel trajectory prediction,

arXiv:2604.04036v2 Announce Type: replace-cross Abstract: Novice math teachers often encounter students' mistakes that are difficult to diagnose and remediate. Misconceptions are especially challengin

arXiv:2609.10632v1 Announce Type: cross Abstract: Machine-learning systems are built almost exclusively on a few large Python-orchestrated frameworks, and they inherit those stacks' engineering costs:

Truman Dickerson / Business Insider: OpenAI says it's no longer sponsoring Caltech's math hackathon, where participants use AI to solve research problems, following criticism of “slop mathematics” — T

arXiv:2609.09203v1 Announce Type: new Abstract: Existing benchmarks for autonomous AI scientists evaluate only final outputs---generated code, hypotheses, or papers---yet discard the reasoning process

arXiv:2609.09664v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversatio

arXiv:2609.11144v1 Announce Type: cross Abstract: Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it to extract market signal. This assumes the two ev

arXiv:2609.09219v1 Announce Type: cross Abstract: AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Discovery Certification Protocol

arXiv:2609.10883v1 Announce Type: cross Abstract: Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this

arXiv:2609.10923v1 Announce Type: new Abstract: Graph captions should help readers understand graph structure, rather than simply translate adjacency matrices into long textual edge lists. A useful gr

arXiv:2609.10745v1 Announce Type: new Abstract: Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work m

TLDR (written by AI because I can't be bothered to write short pieces for short attention spans. Original piece written with my own two thumbs): Today’s frontier models can’t “copy themselves like a v

arXiv:2609.11014v1 Announce Type: new Abstract: Long-horizon goal-conditioned reinforcement learning delegates control to a high-level module that proposes subgoals, but existing subgoals are implicit

arXiv:2609.10934v1 Announce Type: new Abstract: Turn-taking is a fundamental mechanism that governs when interlocutors speak and listen. Although Spoken Dialogue Systems (SDS) exploit a range of lingu

Very cool paper on memory compression for agents. If you run many agent sandboxes in parallel for RL or evals, memory becomes highly redundant. This work suggests that compressing against that redunda

arXiv:2609.11198v1 Announce Type: cross Abstract: Generative AI and the practice of 'vibe coding' are changing how archaeologists carry out computational research, but their effects on the discipline'

arXiv:2609.07334v1 Announce Type: new Abstract: The Asset Administration Shell (AAS) is a cornerstone of Industry 4.0 and the Digital Product Passport, providing standardized digital representations o

arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate

Another brilliant paper from Meta. This one is worth reading if you work on production-grade ranking or recommendation systems. Meta deployed an autonomous agent that runs the ML iteration cycle acros

arXiv:2609.05802v1 Announce Type: cross Abstract: Large language models answering questions over multi-page documents are expected to cite the supporting pages, yet supplied citations are sometimes in

arXiv:2609.06879v1 Announce Type: cross Abstract: Steering vectors have rapidly emerged as a popular and effective method for guiding the output of LLMs in very specific ways. But constructing accurat

arXiv:2609.10366v1 Announce Type: cross Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true g

arXiv:2609.05637v2 Announce Type: replace Abstract: A popular way to improve Retrieval-Augmented Generation (RAG) is to rewrite the user's question into several variants and search with all of them. W

arXiv:2609.10008v1 Announce Type: new Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gall

arXiv:2408.10608v2 Announce Type: replace Abstract: Large language models (LLMs) may encode biased associations from heterogeneous training corpora that are not immediately visible under ordinary prom

arXiv:2609.09578v1 Announce Type: cross Abstract: Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objec