Knowledge catalogue
arXiv:2610.06672v1 Announce Type: new Abstract: Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended
arXiv:2610.05322v1 Announce Type: new Abstract: Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We in
arXiv:2610.03383v1 Announce Type: new Abstract: Attack Path (AP) modeling is fundamental to cybersecurity analysis, where the Planning Domain Definition Language (PDDL) has been widely adopted to enco
arXiv:2606.17454v3 Announce Type: replace Abstract: AI agent performance is not just a modeling problem, it is fundamentally a systems problem. The advanced capabilities of models are realized through
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources
arXiv:2610.03675v1 Announce Type: cross Abstract: LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as
arXiv:2603.29112v2 Announce Type: replace Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in rec
arXiv:2610.02488v1 Announce Type: new Abstract: Language-model agents increasingly rely on harnesses that manage bounded context, persistent memory, tools, verification, and repeated execution, yet ex
arXiv:2610.02396v1 Announce Type: cross Abstract: Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficul
arXiv:2610.02738v1 Announce Type: new Abstract: Differentially private training clips each per-example gradient before adding noise. This clipping is radial for each example, yet unequal clipping fact
arXiv:2610.03695v1 Announce Type: new Abstract: Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language mode
arXiv:2610.02982v1 Announce Type: new Abstract: Programmable logic controllers (PLCs) coordinate industrial equipment by reading sensor inputs and issuing control commands. Evaluating whether large la
arXiv:2610.02404v1 Announce Type: cross Abstract: We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simpl
arXiv:2505.13439v2 Announce Type: replace-cross Abstract: Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT)
arXiv:2610.03567v1 Announce Type: new Abstract: We describe the Writerslogic team's participation in the CLEF 2026 SimpleText shared task, addressing Task 1 (text simplification) and Task 2 (complexit
Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, verify them before running one, and spend more on the verifie
Whenever I feed codebases into local models (Qwen, DeepSeek R1) or API models, the biggest annoyance is prompt pollution: - Lockfiles (`Cargo.lock`, `package-lock.json`) burning 30,000+ tokens for zer
From the first LLaMA 33B I knew I wanted that magic-like intelligence locally, mine, so nobody could take it away when I needed it. I bought a 3090 for my home PC. Then LLaMA 65B appeared and I was
First of all, thank you for reading. I trained a small MoE model completely from scratch (no external base weights) and wanted to share the results + a couple of lessons. Apex-2 - Architecture: Decode
So I tried that miracle engine everyone is talking about. Asked the IQ3_S model to express its opinion on a post from this sub to measure the tps on a long-ish generation: Can you help with the follow
Nonobench measures how well LLMs solve nonograms (picross). Each model gets the row and column clues once and returns the full grid. No tools, one attempt per puzzle. Method: - Standard mode: 30 puzzl
We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agent
LWiAI Podcast #258 (recorded 26‑Sep‑2026) reviews major AI updates from the previous week. Key developments include Anthropic’s Opus 5.5 release—offering lower pricing, faster performance and robust b
Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for real world docs (ins
This is actually two models: Qwen Image 2.1 Fix v2.0 and Qwen Image 2.1 Fix Opinionated v1.0. The former surgically targets Qwen's weird noise and messy details with almost no effect on composition, a
arXiv:2610.00376v1 Announce Type: new Abstract: We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet tim
arXiv:2610.01821v1 Announce Type: new Abstract: Understanding information processing in large language models (LLMs) requires dissecting the geometric organization of their internal token representati
arXiv:2610.00316v1 Announce Type: cross Abstract: Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored. We
arXiv:2610.02173v1 Announce Type: new Abstract: Ablate a component of a language model, and other components often appear to adjust and compensate. This phenomenon, termed self-repair, has been observ
arXiv:2610.01535v1 Announce Type: cross Abstract: Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparato
For folks not understanding where we are at with AI now - if the task is verifiable, it is now solved by AI. Yes, earlier days you could argue that 'AI isn't that good' (e.g. see first attached chart
arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended s
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termin
Hey local AI community, I've been working on this for a while and finally feel ok sharing it. It's a cyber benchmark where the model gets a shell in an isolated docker box and has to find the exact fl
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive,
arXiv:2610.01079v1 Announce Type: cross Abstract: Machine-learning Network Intrusion Detection Systems (IDS) depend on substantial labeled datasets and task-specific training, whereas Large Language M
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source h
arXiv:2610.01393v1 Announce Type: cross Abstract: Constructing typed, justified semantic links between ontologies is essential for enabling interoperability across heterogeneous and interdisciplinary
arXiv:2601.07148v4 Announce Type: replace-cross Abstract: Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchm
arXiv:2610.02002v1 Announce Type: cross Abstract: Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a re
arXiv:2505.17613v2 Announce Type: replace Abstract: Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align with human evaluation,
one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to get 93%-96%+ on lon
arXiv:2610.02204v1 Announce Type: cross Abstract: Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integr
arXiv:2502.14994v2 Announce Type: replace Abstract: The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on speci
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving r
arXiv:2610.00253v1 Announce Type: cross Abstract: Audits of AI visibility summarise the brand recommendations of deployed language models into per-system profiles. We test whether such a profile descr
Something keeps happening in frontier AI, and the explanation we are given is always one size larger than the event. An OpenAI research model, running in a supposedly offline training environment, hit
The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of
This is beautiful work @huggingface! 🤗 The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guid
arXiv:2610.01022v1 Announce Type: new Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory re
arXiv:2609.39238v1 Announce Type: new Abstract: An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, eac
arXiv:2609.39027v1 Announce Type: new Abstract: AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentially rewarding rhetorical optimizat
arXiv:2609.38737v1 Announce Type: new Abstract: Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separat
arXiv:2601.02641v2 Announce Type: replace Abstract: Despite its efficiency, there has been little research on the practical aspects required for real-world deployment of on-device AI models, such as t
arXiv:2603.28005v2 Announce Type: replace Abstract: When an LLM judge only has to assign a three-way support label to a candidate answer given a reference, does asking it to decompose the answer into
arXiv:2609.39188v1 Announce Type: new Abstract: Developmental psychology holds that certain priors are given to infants prior to experience rather than induced from data, and that the influence of suc
arXiv:2609.38820v1 Announce Type: cross Abstract: With the rapid growth of Arabic NLP, several models, datasets and benchmarks have been reported. This paper asks whether approaches developed for majo
arXiv:2609.39139v1 Announce Type: new Abstract: Adaptive RAG uses signals such as confidence, relevance, support, and retrieval quality to decide when to search or correct evidence. In multi-step retr
arXiv:2607.14576v2 Announce Type: replace Abstract: Whether a deep residual architecture trains stably is usually determined by training it, which is expensive and answers the question only for the ar
arXiv:2609.38222v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated clai