Knowledge catalogue
arXiv:2608.16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task. We ask whether it finished it within policy. We introduce Fiducia-bench, a benchmark
arXiv:2608.15032v1 Announce Type: cross Abstract: Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional a
arXiv:2608.15535v1 Announce Type: new Abstract: We present L3Cube-IndicQuest v2, a large-scale gold-standard multilingual question-answering benchmark for evaluating the India-specific factual knowled
arXiv:2608.16508v1 Announce Type: cross Abstract: We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from het
arXiv:2608.14625v1 Announce Type: cross Abstract: Academic peer review is under mounting strain: NeurIPS 2025 received 21,575 submissions, ICLR 2025 received 11,603, and ICML 2025 received 12,107. Thi
arXiv:2608.14683v1 Announce Type: new Abstract: Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for re
arXiv:2608.14606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the
arXiv:2608.16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a f
Qwen 27B is the 'DeepSeek moment' for open source. It matches the closed-source state-of-the-art from just a few months ago and runs on an RTX 5090. Without exaggeration, it’s a game changer. let that
arXiv:2608.16786v1 Announce Type: new Abstract: Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We stud
arXiv:2608.15787v1 Announce Type: cross Abstract: Two Mixture-of-Experts (MoE) forward passes can share every weight yet route the same token through different experts. This creates a possible blind s
Stable Audio 3.0 now offers a DAW‑plugin that brings real‑time audio generation directly into your favorite digital audio workstation, letting you arrange, edit, and mix generated tracks like any othe
Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it can do! ⚡ It's official: Qwen3.8-27B just scored 52 on the @ArtificialAnlys Intelligence Index. We
arXiv:2608.14838v1 Announce Type: cross Abstract: Retrieval components for code assistants are tuned against retrieval metrics: a configuration that raises recall@k is adopted, and downstream task suc
arXiv:2608.14876v1 Announce Type: cross Abstract: Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This
arXiv:2608.14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as 'fair, clear, and not misleading' or 'deliver good outcomes', cannot be reduced to binar
arXiv:2608.14320v1 Announce Type: new Abstract: The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in h
arXiv:2608.13766v1 Announce Type: new Abstract: Vision-language models (VLMs) remain unreliable on chart questions that require reasoning over visual quantities, and this weakness is usually attribute
arXiv:2608.14414v1 Announce Type: new Abstract: Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunolog
arXiv:2608.14303v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Exis
arXiv:2608.13958v1 Announce Type: new Abstract: How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating
arXiv:2608.13580v1 Announce Type: cross Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric la
Hi all! I finally just got around to testing out Qwen 3.8 27b. I'm using Unsloth's UD-Q8_K_XL quant as a sit-in replacement to Qwen 3.6 27b, same quant size. Wow -- this thing isn't messing around. I
arXiv:2608.13959v1 Announce Type: new Abstract: Function calling is what the recent accounting of constrained generation explicitly sets aside: it finds the decoder's contribution small for format con
arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference. We study a different possibility: stable mi
arXiv:2608.14399v1 Announce Type: cross Abstract: Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermedia
A short illustration of how the Claude's watermarking is supposed to work (based on my read of their released materials). In general, when we are generating tokens, there can be multiple high-scoring
Muse Glimmer Cookbook Clone it, run it on the GPU you already own, and ship a working agent — one that plans, calls tools, and self-corrects — in a single sitting, fully offline. Muse Glimmer is an op
The two leading labs are already feeling extremely threatened by Qwen & friends, however I think there are tons of enterprises and organizations in the West that don't feel comfortable using Chinese m
arXiv:2608.12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few
arXiv:2608.12894v1 Announce Type: new Abstract: Cultural evaluation of large language models (LLMs) often focuses on high-resource standard languages, leaving regional culture and dialect communities
arXiv:2608.12547v1 Announce Type: cross Abstract: Large language model agents deployed without a central controller are often assumed to require communication to coordinate their actions. We ask what
arXiv:2608.13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies. We ask a narrower question: once a model sits in a workflo
arXiv:2608.12852v1 Announce Type: cross Abstract: Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally disting
arXiv:2608.12611v1 Announce Type: new Abstract: Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible detai
arXiv:2608.13315v1 Announce Type: cross Abstract: We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may
arXiv:2608.13450v1 Announce Type: cross Abstract: Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking,
arXiv:2608.12928v1 Announce Type: new Abstract: We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licens
arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signa
arXiv:2608.12330v1 Announce Type: new Abstract: The detection of online sexism remains an open problem. Sexism detection is inherently subjective, yet most existing systems reduce multi-annotator labe
arXiv:2608.12564v1 Announce Type: new Abstract: Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as moder
arXiv:2608.13167v1 Announce Type: cross Abstract: When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distingui
arXiv:2608.12138v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but s
arXiv:2608.11247v1 Announce Type: new Abstract: Recent advances in language models have enabled collaborative settings in which multiple models leverage one another's capabilities, iteratively improvi
arXiv:2608.11889v1 Announce Type: cross Abstract: Prompting-based (extit{i}.extit{e}., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the ta
arXiv:2608.11210v1 Announce Type: new Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter. Despite decades of methodological work, researchers
arXiv:2608.11513v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software engineering workflows, helping developers write, debug, test, and maintain code
arXiv:2608.11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retr
arXiv:2608.11683v1 Announce Type: new Abstract: AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existi
arXiv:2608.11787v1 Announce Type: cross Abstract: Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment,
arXiv:2608.11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and re
arXiv:2603.20895v3 Announce Type: replace Abstract: Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task diff
arXiv:2608.11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that
There is much less signal in agent leaderboards than the rankings imply. A four-facet Generalizability Theory decomposition across TheAgentCompany, tau-squared-bench, and AppWorld finds the agent main
arXiv:2608.12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities
As agentic AI infrastructure moves from experimentation into production, enterprises are confronting a more complex question than which model to use: how to control the cost, data exposure and infrast
arXiv:2608.10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server
arXiv:2608.10567v1 Announce Type: new Abstract: Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and n
arXiv:2608.11025v1 Announce Type: new Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leadi
arXiv:2608.10300v1 Announce Type: new Abstract: Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human re