Knowledge catalogue
arXiv:2608.29446v1 Announce Type: new Abstract: Judgments about psychological distress are socially situated: what counts as concerning hinges on community norms around emotional expression, vulnerabi
A secret that leaks into shipped code is a breach waiting to happen. @FactoryAI's droids write and commit code faster than any reviewer can keep up, so Droid Shield has to be trustworthy and low-frict
Anthropic: Anthropic details security efforts following Claude cyber evaluation incidents, including a weeks-long pause on higher-risk RL and work to curb reward hacking — On July 30, we reported thre
arXiv:2608.28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning:
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common u
arXiv:2608.27925v1 Announce Type: new Abstract: Entity-Memory graph retrieval keeps dialogue turns as verbatim Memory nodes, links repeated mentions through shared Entities, and connects adjacent Memo
arXiv:2305.12474v4 Announce Type: replace Abstract: Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensive
arXiv:2602.18154v3 Announce Type: replace Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vul
arXiv:2608.27531v1 Announce Type: cross Abstract: The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the m
Just WOW! Absolutely unacceptable. I look forward to understanding how that is possible. LLM tools get going and you can’t be 100% certain what they’re gonna do. Just like any LLM, you can ask coding
My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the
potentially MUCH more serious than the OpenAI Hugging Face incident — but lacks the vivid “civilizational” drama. so few people are paying attention. Oh fuck. Agents like Claude, Codex and Hermes are
arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ab
arXiv:2608.28099v1 Announce Type: cross Abstract: Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current appr
A hallucinated event, Crono awakens in his modest bedroom of 2095... I am using local models since 2025 January. My daily driver is qwen 3.6 35B A3B, which works pretty well for coding tasks, but I al
arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according
I built SpeakoFlow Mini, an Apache-2.0 fine-tune of Qwen3.5-0.8B for dictation cleanup. It is not a chat model or a general rewriter. It takes speech-to-text output, applies corrections the speaker ac
// Your LLM judge disagrees with the experts // LLM Judges can be tricky to build. Here is an interesting showcasing why: There propose a reference-full benchmark of hundreds of complete human-to-huma
at the end of the day, we all have to stand by our company and the values it represents 🙂 * frontier labs will want to own their own application/harness/model e2e. or at least, openai will to start wi
The official benchmark card for Ling-3.0-flash-Fin is a useful reminder that the unit being tested is rarely just “the model.” The release says most runs used temperature 1, top_p 0.95 and the highest
arXiv:2608.26867v1 Announce Type: new Abstract: Large language model agents reason, call tools, and act autonomously over many steps, but their agentic skills-correctly sequencing tools, planning unde
arXiv:2608.26143v1 Announce Type: cross Abstract: Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their a
arXiv:2608.26716v1 Announce Type: new Abstract: Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic desig
arXiv:2608.27334v1 Announce Type: new Abstract: Industrial sites contain large volumes of read-only telemetry, but few benchmarks specify how to compile these records into executable multi-turn agent
arXiv:2608.26846v1 Announce Type: cross Abstract: Interactive language-model agents use confidence signals to decide whether to answer immediately, retrieve additional evidence (from memory or externa
arXiv:2608.26110v1 Announce Type: cross Abstract: Large Language Models (LLMs) are emerging as promising assistants in High-Performance Computing (HPC), where programming remains complex and expertise
arXiv:2608.26310v1 Announce Type: new Abstract: Large language models can now generate complex, multi-step mathematical proofs, but reliably determining their correctness and localizing early logical
arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selecti
arXiv:2606.21891v2 Announce Type: replace Abstract: Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate th
arXiv:2608.27296v1 Announce Type: new Abstract: We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory con
arXiv:2608.26848v1 Announce Type: cross Abstract: Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated dat
arXiv:2608.26317v1 Announce Type: cross Abstract: Frontier language models are increasingly marketed as omni systems that can perceive and respond across modalities. Existing evaluation frameworks, ho
arXiv:2608.26866v1 Announce Type: new Abstract: Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ca
arXiv:2608.27161v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled a shift from sentence-level to document-to-document (Doc2Doc) machine translation, promising improved global c
arXiv:2608.26971v1 Announce Type: new Abstract: In recent years, image-to-video (I2V) generation models have made remarkable progress in subject consistency and temporal coherence, enabling high quali
arXiv:2601.13029v4 Announce Type: replace Abstract: While Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by 2D-centric paradigm that severely limits genuine 3D
Frederic Lardinois / The New Stack: Z.ai releases GLM-5.3's weights under a new license requiring companies with 10B+ in revenue over 12 months to pass Z.ai's security review to host the model — Z.ai
arXiv:2606.19660v2 Announce Type: replace-cross Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applicatio
arXiv:2608.25379v1 Announce Type: new Abstract: Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning and create a failure mode that final-an
If you maintain a skill library for long-horizon agents, this one is worth your time. (bookmark it) It discusses one of most common topics I get asked about these days. It shares some good ideas on ho
arXiv:2608.25593v1 Announce Type: new Abstract: Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/s
Neat paper suggesting that human augmentation and task automation are not necessarily related. Models that are really good at doing work are not always good at helping humans do work better. Given the
arXiv:2603.11051v2 Announce Type: replace-cross Abstract: We release OpenSanctions Pairs, the first large-scale public benchmark for entity matching on sanctions and OSINT data. The dataset includes 7
arXiv:2608.25005v1 Announce Type: new Abstract: The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models freq
arXiv:2608.25924v1 Announce Type: new Abstract: This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning ma
arXiv:2603.10068v2 Announce Type: replace-cross Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to c
arXiv:2507.21790v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are becoming widely used to support various workflows across different disciplines, yet their potential in discre
arXiv:2608.24191v1 Announce Type: cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine
Great new paper from AWS on agent handoff tax. If you build agents today, you need to understand the so-called handoff tax. (bookmark it) Escalating to a stronger model mid-run is usually the resort w
arXiv:2608.24534v1 Announce Type: new Abstract: Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. We investigate whether safety alignment can be impro
arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We in
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems
arXiv:2608.24804v1 Announce Type: new Abstract: We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include
arXiv:2608.24777v1 Announce Type: new Abstract: LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modifi
arXiv:2608.24113v1 Announce Type: cross Abstract: Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or
arXiv:2608.24358v1 Announce Type: new Abstract: Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-qu
arXiv:2608.22894v1 Announce Type: cross Abstract: Arabic harmful-language detection has received considerable attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a
arXiv:2608.22322v1 Announce Type: new Abstract: Low-precision optimizer-state methods are commonly designed for dense Adam-style moments, but memory-efficient optimizers maintain factored, confidence-
arXiv:2608.21864v1 Announce Type: cross Abstract: The current progress of Clinical Vision Large Language Models (C-VLLMs) has substantially improved digital diagnostics, still these frameworks often e
arXiv:2608.22808v1 Announce Type: new Abstract: When can an agent failure be caught? An audit is usually limited by the record rather than by the method. CatchBench therefore puts one auditor's questi