Knowledge catalogue
arXiv:2601.21543v3 Announce Type: replace Abstract: Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent em
arXiv:2606.09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the ga
arXiv:2512.06343v3 Announce Type: replace-cross Abstract: Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling
arXiv:2606.08367v1 Announce Type: cross Abstract: Most evaluations of LLM agents look like exams: a discrete task, a clean environment, a score in minutes or hours. We argue that this approach is mism
arXiv:2606.09800v1 Announce Type: cross Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle. Ho
arXiv:2510.09783v2 Announce Type: replace-cross Abstract: Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minor
arXiv:2606.08919v1 Announce Type: new Abstract: As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approva
arXiv:2602.02572v2 Announce Type: replace-cross Abstract: Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regulariza
arXiv:2606.08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for
what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the evidence? and if you can agree that “If you ask an LLM a question it can't answer, sometimes it
arXiv:2606.06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale re
arXiv:2606.06054v1 Announce Type: new Abstract: Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are l
arXiv:2606.05252v1 Announce Type: cross Abstract: Security teams routinely simulate attacks against their own systems to check whether their monitoring would catch a real intruder. These Breach-and-At
arXiv:2603.26233v2 Announce Type: replace Abstract: As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspeci
arXiv:2606.05513v1 Announce Type: cross Abstract: Epidemic LLM forecasters are usually trained and evaluated as static supervised models, whereas operational pandemic forecasting is a streaming proces
arXiv:2606.06473v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE),
arXiv:2606.05828v1 Announce Type: cross Abstract: As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerg
arXiv:2505.19293v2 Announce Type: replace-cross Abstract: Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effort
arXiv:2512.06553v2 Announce Type: replace-cross Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated b
arXiv:2606.04484v1 Announce Type: new Abstract: We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks t
Release b9509 is a build version of llama.cpp, which provides LLM inference in C/C++ . As a specific build identifier in the llama.cpp project's release history, it likely contains bug fixes, performa
b9512 is a release build of llama.cpp, which provides LLM inference in C/C++ . The release uses a version numbering system with 'b' prefixes for intermediate builds, with newer releases building upon
arXiv:2606.05002v1 Announce Type: new Abstract: LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual mo
arXiv:2606.04037v1 Announce Type: new Abstract: Pre-deployment verification of enterprise artificial intelligence (AI) agents remains a critical gap between large language model (LLM) capability bench
arXiv:2606.02644v1 Announce Type: cross Abstract: Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domai
arXiv:2601.09869v2 Announce Type: replace Abstract: Anthropomorphisation -- the phenomenon whereby non-human entities are ascribed human-like qualities -- has become increasingly salient with the rise
arXiv:2606.03239v1 Announce Type: new Abstract: LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on o
arXiv:2606.02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to i
arXiv:2606.02994v1 Announce Type: new Abstract: ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We intro
arXiv:2606.03197v1 Announce Type: new Abstract: Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utilize information accumulated across extended interac
arXiv:2606.03085v1 Announce Type: cross Abstract: Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways link
arXiv:2606.02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention te
arXiv:2512.16310v3 Announce Type: replace-cross Abstract: LLM-based agents increasingly use multiple external tools to complete complex tasks. We study Tools Orchestration Privacy Risk (TOP-R): an age
Ship multilingual features in hours, not months Your translation workflow probably looks like this: one vendor for real-time chat, another for document translation, a custom LLM integration for nuance
The search results don't contain specific information about release b9470. Based on available context, b9470 is a build release from llama.cpp, a C/C++ implementation that enables LLM inference with m
arXiv:2606.02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approac
arXiv:2601.19921v2 Announce Type: replace-cross Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows tha
arXiv:2602.06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scrip
arXiv:2603.23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent d
arXiv:2606.01873v1 Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embed
arXiv:2606.01779v1 Announce Type: new Abstract: LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent
arXiv:2504.16129v5 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (LaMAS) have demonstrated strong capabilities on complex agentic tasks requiring multifac
arXiv:2606.02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and halluci
arXiv:2602.06448v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencie
arXiv:2606.02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabili
arXiv:2606.01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory,
arXiv:2606.00822v1 Announce Type: cross Abstract: Skill-based LLM agents increasingly rely on long procedural documents, but full-document prompting wastes tokens and dilutes information critical to e
arXiv:2606.00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set. We study a core safety problem in agen
arXiv:2605.30667v1 Announce Type: cross Abstract: Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis witho
arXiv:2605.31149v1 Announce Type: cross Abstract: This study investigates how UX research (UXR) principles, combined with Large Language Model (LLM)-supported analysis, can be used to improve the qual
arXiv:2605.30947v1 Announce Type: new Abstract: LLM-based research agents have advanced rapidly in science and engineering, where research is organized around executable experiments, code, and quantit
Processing millions of user reviews in real-time, under strict latency and cost constraints, is no easy task. Trustpilot has been doing exactly that with custom machine learning since long before larg
LangSmith is a development platform designed to build, test, and monitor LLM applications, offering tools for debugging and evaluation to improve AI application quality and reliability. The statement
arXiv:2605.30785v1 Announce Type: new Abstract: LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause lon
arXiv:2605.31404v1 Announce Type: cross Abstract: Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster map
Release b9433 is a version update from the llama.cpp project, which provides LLM inference in C/C++. Based on the GitHub releases structure, this is a specific build iteration that would contain impro
arXiv:2605.29489v1 Announce Type: new Abstract: Weight-space model merging is usually formulated as an algebraic operation on checkpoints, yet at LLM scale the limiting resource is often the set of ex
arXiv:2605.29116v1 Announce Type: new Abstract: When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating
Welcome to the second Cloud CISO Perspectives for May 2026. Today, Usman Chaudhary, Field CISO, Google Public Sector, offers a guide for CISOs protecting government agencies and critical infrastructur
arXiv:2605.29055v1 Announce Type: new Abstract: Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-agent pipelines where unsupported claims can propaga