Knowledge catalogue
Another interesting approach to self-evolve agent skills. But it's important to know that skill self-evolution loops fail in two specific ways: 1. Direction instability. Effective corrections get over
arXiv:2609.07712v1 Announce Type: new Abstract: Mobile GUI agents can execute tasks from natural-language instructions, but their evaluation remains difficult to make both realistic and reproducible.
arXiv:2603.16112v2 Announce Type: replace-cross Abstract: Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked e
arXiv:2603.01690v3 Announce Type: replace-cross Abstract: While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-ba
arXiv:2609.10137v1 Announce Type: new Abstract: A hallmark of human dexterity is the cooperative use of fingers, where different fingers take on distinct yet coordinated roles to accomplish fine manip
arXiv:2609.05446v1 Announce Type: new Abstract: We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent sta
arXiv:2609.05794v1 Announce Type: cross Abstract: Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions
arXiv:2602.14488v3 Announce Type: replace-cross Abstract: IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state ha
arXiv:2609.05824v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many
arXiv:2609.09575v1 Announce Type: new Abstract: Topic models summarize large text corpora, but top-ranked words often provide only a limited representation of topic semantics. Sparse autoencoders (SAE
arXiv:2609.10445v1 Announce Type: new Abstract: Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: mo
arXiv:2609.09468v1 Announce Type: new Abstract: Can an agent learn a numerical search strategy through executable practice and then transfer that strategy as text? We study low-budget black-box optimi
arXiv:2609.09659v1 Announce Type: new Abstract: Federated learning shares model updates rather than raw data, yet these updates can be inverted to reconstruct the clients' training data. Analytic reco
arXiv:2609.07434v1 Announce Type: new Abstract: Natural-language Computer-Aided Design (CAD) code generation aims to turn design intent into executable and editable parametric programs. Large language
arXiv:2609.08094v1 Announce Type: new Abstract: Large Language Models are increasingly deployed in public-sector settings, where incorrect guidance can cause irreversible harm. We introduce CIVI, the
arXiv:2609.07798v1 Announce Type: cross Abstract: Natural Language Processing (NLP) in the climate domain requires models to process heterogeneous text sources, including scientific literature, policy
arXiv:2609.10158v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositio
arXiv:2609.09370v1 Announce Type: new Abstract: Discrete black-box optimization is often addressed using approaches such as Sequential Model-Based Optimization (SMBO), which aims to improve sample eff
arXiv:2609.10495v1 Announce Type: new Abstract: In real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Base
arXiv:2609.06126v1 Announce Type: new Abstract: We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different
arXiv:2609.09413v1 Announce Type: cross Abstract: Choosing a recovery process for scale-up requires connecting laboratory results with product requirements, process costs, and scale effects. We analyz
Original Source from DeepSeek WeChat Official Account: https://mp.weixin.qq.com/s/qg0NU3NNUbp1co2PdkAPAg Today we're officially releasing the DeepSeek V4.1 Flash model. It is the smallest model in our
arXiv:2609.09254v1 Announce Type: new Abstract: Field-programmable gate arrays (FPGAs) enable efficient neural-network inference, but most deployment flows either accelerate multiply-accumulate operat
arXiv:2609.05779v1 Announce Type: cross Abstract: Large language models used for code editing can be trained and deployed in at least two output regimes: direct generation, where the model emits the e
arXiv:2609.10253v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situations
arXiv:2609.09737v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from nois
arXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large fo
arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, how
arXiv:2609.07879v1 Announce Type: new Abstract: Large Language Models (LLMs) are frequently confident, eloquent, and well versed. A natural question arises: do they know what they don't know? To answe
arXiv:2609.09425v1 Announce Type: new Abstract: Educational data filters have become a practical way to improve language-model pre-training, but most filters treat educational value as a single scalar
arXiv:2609.09728v1 Announce Type: new Abstract: Source-level analysis of interictal epileptiform discharges (IEDs) is relevant to presurgical evaluation and treatment planning because it helps charact
arXiv:2609.10387v1 Announce Type: new Abstract: Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exce
arXiv:2609.08267v1 Announce Type: new Abstract: Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring fact
arXiv:2609.08435v2 Announce Type: new Abstract: In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier informati
arXiv:2609.06155v1 Announce Type: cross Abstract: Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Desp
arXiv:2609.06063v1 Announce Type: new Abstract: AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human ove
arXiv:2609.09367v1 Announce Type: new Abstract: Divergence-based regularization and Sharpness-Aware Minimization (SAM) are two prominent approaches for improving generalization in deep learning, both
arXiv:2609.05806v1 Announce Type: new Abstract: Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide r
arXiv:2609.08407v1 Announce Type: new Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qw
arXiv:2410.08776v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learning
arXiv:2609.09768v1 Announce Type: cross Abstract: In Retrieval-Augmented Generation (RAG) systems, a large number of retrieved chunks are concatenated to form the input context so that users can recei
arXiv:2609.06403v1 Announce Type: new Abstract: Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as i
arXiv:2609.07984v1 Announce Type: new Abstract: Process mining has long turned event logs into process knowledge: discovered models, conformance evidence, bottleneck diagnoses, and runtime predictions
arXiv:2609.09476v1 Announce Type: cross Abstract: In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, makin
arXiv:2609.07573v1 Announce Type: new Abstract: Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents
arXiv:2609.10166v1 Announce Type: new Abstract: UAV target following in cluttered environments is inherently predictive: current-state followers can lag behind turns, choose blocked corridors, or trad
Great paper from AWS. I use a similar setup where an agent orchestrator sits on top of a multi-agent system. (bookmark it) This work introduces one of the many approaches available to manage compound
arXiv:2609.09941v1 Announce Type: new Abstract: Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex
arXiv:2609.10225v1 Announce Type: new Abstract: Feature transformation improves predictive performance on tabular data by constructing informative abstractions from raw features. Recent generative app
NVIDIA’s BioNeMo Inference Runtime (BioIR) accelerates biomolecular structure‑prediction models on GPUs while preserving the familiar PyTorch workflow by providing an end‑to‑end pipeline that handles
arXiv:2609.07662v1 Announce Type: cross Abstract: Large language models are increasingly used as sources of advice and information, including in high-stakes settings, yet little is known about how the
arXiv:2609.09793v1 Announce Type: cross Abstract: Directional ablation removes an aligned language model's ability to refuse by projecting a single 'refusal direction' out of the weights that write th
NVIDIA’s Nemotron 3 Ultra NIM 2.0.12 stack boosts a 4×B200 system’s throughput by up to 2.5 ×, achieving roughly 1,997 tokens per second at a target of 50 transactions‑per‑user through autotuned kerne
arXiv:2609.09626v1 Announce Type: new Abstract: Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annota
arXiv:2609.10494v1 Announce Type: new Abstract: Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet a
arXiv:2609.06960v1 Announce Type: new Abstract: Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking
arXiv:2609.09210v1 Announce Type: cross Abstract: Teleoperated demonstrations are often multimodal even when the underlying dynamics are nearly deterministic given the executed action. We argue that t
arXiv:2609.09953v1 Announce Type: new Abstract: Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot le
arXiv:2609.06792v1 Announce Type: new Abstract: Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underex