Knowledge catalogue
Banger paper from the Qwen team. If you evaluate agents on anything longer than a single session, this one is worth your time. (bookmark it) E-Commerce Bench runs an agent through a simulated 365-day
arXiv:2608.29990v1 Announce Type: cross Abstract: Large language models are increasingly deployed in Arabic-speaking markets, yet standard benchmarks overwhelmingly reward Modern Standard Arabic (MSA)
arXiv:2606.15932v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual ar
arXiv:2508.14323v3 Announce Type: replace Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none
arXiv:2608.28725v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final-
arXiv:2608.29887v1 Announce Type: new Abstract: Multiple-choice question answering (MCQA) benchmarks in NLP use number-right scoring (accuracy), but in educational testing, the scoring scheme, the com
arXiv:2608.30498v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deducti
arXiv:2608.29644v1 Announce Type: cross Abstract: Attributing an artwork to an artist has traditionally relied on detailed visual observations and descriptions, known as stylistic analysis in art hist
arXiv:2608.30315v1 Announce Type: cross Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lan
arXiv:2608.28631v1 Announce Type: new Abstract: An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model fam
arXiv:2608.28843v1 Announce Type: cross Abstract: We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output or
arXiv:2608.29966v1 Announce Type: new Abstract: Domain adaptation of large language models increasingly depends on constructing high-quality training data, yet existing data-preparation pipelines typi
arXiv:2608.28837v1 Announce Type: cross Abstract: We conducted an interview study with twelve students on their use of generative AI in academic communication. Students delegated professional messages
arXiv:2608.30405v1 Announce Type: new Abstract: Medical knowledge changes continually, making large language models vulnerable to relying on outdated yet clinically plausible information. We study whe
arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete pa
arXiv:2603.16622v2 Announce Type: replace Abstract: Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by de
arXiv:2608.30893v1 Announce Type: new Abstract: Electrocardiogram (ECG) interpretation requires knowledge of cardiology, electrophysiology, clinical diagnosis, ECG waveforms, signal acquisition, and i
arXiv:2608.30021v1 Announce Type: cross Abstract: Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are ofte
arXiv:2511.14086v2 Announce Type: replace-cross Abstract: Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. Th
arXiv:2506.11635v2 Announce Type: replace-cross Abstract: Credit card fraud mitigation plays a significant role in modern society. While fraud detection systems are essential, they often struggle to k
arXiv:2608.28687v1 Announce Type: new Abstract: Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However,
arXiv:2608.30046v1 Announce Type: cross Abstract: Noisy labels remain a critical challenge for training deep neural networks, since memorizing incorrect labels degrades generalization. Once noisy samp
arXiv:2608.29615v1 Announce Type: cross Abstract: Across industries, machine-learning systems support applications ranging from prediction and anomaly detection to forecasting, optimization, and sched
arXiv:2606.12683v2 Announce Type: replace Abstract: Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade ta
arXiv:2608.28619v1 Announce Type: cross Abstract: Medical history taking is a dialogue-based clinical reasoning task in which learners must gather, organise, and integrate patient information while th
arXiv:2509.23263v3 Announce Type: replace Abstract: Long-horizon GUI automation remains challenging due to error accumulation over extended interaction sequences. Process Reward Models (PRMs) provide
arXiv:2608.29193v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can assign similar confidence to answers that fail for different reasons. We propose HalluPrism, a behavioral d
arXiv:2503.04822v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many
arXiv:2608.30468v1 Announce Type: new Abstract: A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at
arXiv:2502.00857v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly provide direct answers to user questions, raising concerns about reduced engagement in critical thinking a
arXiv:2608.28648v1 Announce Type: new Abstract: We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We introduce a benchmark of 41 paired constraints w
Inference workloads fall into four use‑case buckets (Chatbots/Copilots, Agents, Content Generation, Translation), each with distinct token patterns that dictate the required GPU memory and compute. Si
The post explains how a quick, one‑hour audit of AI agent usage revealed $1 million per year in avoidable spend. By reviewing deployment patterns and trimming unnecessary calls, the team reallocated r
arXiv:2602.00685v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and
arXiv:2608.31058v1 Announce Type: new Abstract: When information extraction fails, a natural instinct is to improve the model doing it: for example, by scaling it up or refining its reasoning. In this
arXiv:2608.28629v1 Announce Type: cross Abstract: Existing methods lack a generalized approach to efficiently identify and resolve the diversity of design defects in BIM. Therefore, this study propose
arXiv:2603.15034v2 Announce Type: replace-cross Abstract: This paper replicates and extends the system used in the AuTexTification shared task for authorship attribution of machine-generated texts. Ex
arXiv:2608.30025v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguis
arXiv:2602.06181v2 Announce Type: replace Abstract: Post-training quantization reduces the memory needed to run large language models but alters their social biases in ways that aggregate metrics fail
arXiv:2601.07794v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly evaluated on their ability to perform multi-hop reasoning, i.e., to combine multiple pieces of i
arXiv:2608.30216v1 Announce Type: cross Abstract: Topic models are widely used for content analysis, where users often analyze corpora around predefined labels rather than unordered latent topics. Exi
arXiv:2608.29257v1 Announce Type: new Abstract: Multiple-choice questions (MCQs) are a standard format for evaluating large language models (LLMs), yet the popularity of answer options can confound ev
arXiv:2608.29685v1 Announce Type: new Abstract: Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertaint
arXiv:2608.30679v1 Announce Type: cross Abstract: Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching the
arXiv:2608.30520v1 Announce Type: new Abstract: Automated material handling systems in semiconductor fabs are operated by a material control system (MCS) that must schedule a relay route for every tra
arXiv:2405.18540v3 Announce Type: replace Abstract: Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large langu
arXiv:2606.09389v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses h
arXiv:2608.28553v2 Announce Type: replace Abstract: Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatio
arXiv:2608.27580v2 Announce Type: replace Abstract: Safety guardrails serve as the last line of defense against harmful inputs and outputs of large language models (LLMs), yet they are trained and eva
arXiv:2608.30821v1 Announce Type: cross Abstract: Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observed, giving robot simulation and em
arXiv:2606.17511v2 Announce Type: replace-cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not
arXiv:2608.30114v1 Announce Type: new Abstract: Brazilian Portuguese remains under-served by open language models, and the few that exist are difficult to reproduce and are often compared without meas
arXiv:2608.29617v1 Announce Type: cross Abstract: This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning fo
arXiv:2608.28884v1 Announce Type: new Abstract: We introduce MineCEraft (Minecraft Construction Engineering Benchmark, pronounced mine-see-ee-raft), an easy-to-use, open-source benchmark designed to s
arXiv:2603.21716v2 Announce Type: replace-cross Abstract: Efficient selection among multiple generative models is increasingly important in modern generative AI, where sampling from suboptimal models
arXiv:2608.30563v1 Announce Type: new Abstract: Multimodal Emotion Recognition (MER) systems often suffer from missing modalities in real-world scenarios. Existing methods usually generate, align, or
arXiv:2608.29278v1 Announce Type: new Abstract: Omni-modal large language models are increasingly evaluated on clean text--vision--audio inputs, where every channel is present, synchronized, and readi
arXiv:2608.30237v1 Announce Type: cross Abstract: General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in buildin
arXiv:2608.28886v1 Announce Type: cross Abstract: What does a generation loop gain from learning on its own verified successes? In cycles of generate, verify, select and LoRA-consolidate on online bin
arXiv:2503.00610v2 Announce Type: replace-cross Abstract: Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult to