Knowledge catalogue
arXiv:2609.37655v1 Announce Type: new Abstract: Advancing spatial intelligence in Multimodal Large Language Models (MLLMs) is bottlenecked by the scarcity of complex, scalable 3D question-answer (QA)
arXiv:2609.37522v1 Announce Type: new Abstract: On-policy distillation (OPD) trains compact language agents with teacher feedback on student-generated trajectories. In multi-turn tasks, compounding er
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool
arXiv:2609.32965v2 Announce Type: replace Abstract: Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment of
arXiv:2609.36593v1 Announce Type: cross Abstract: Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be desi
NVIDIA NeMo Relay supplies a common observability layer that captures ordered lifecycle events and structured trajectories—ATOF event streams, ATIF step‑by‑step footprints, and OpenTelemetry spans wit
arXiv:2609.34924v1 Announce Type: new Abstract: An auditor who checks whether a system's weights are frozen is checking the wrong thing. Our stationarity dichotomy says that iterative self-modificatio
arXiv:2609.32783v1 Announce Type: cross Abstract: Before a team of robots moves, each proposed step must be checked for collisions with other robots and with obstacles. We present CollisionGAT, a grap
arXiv:2609.31873v1 Announce Type: new Abstract: Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails. More recently,
Artificial intelligence is changing the makeup of internet traffic, making AI identity an emerging concern for websites and applications. They are no longer interacting only with humans and traditiona
arXiv:2609.35267v1 Announce Type: new Abstract: Large-scale 3D multi-agent path finding becomes increasingly difficult under dense traffic. Priority Inheritance with Backtracking (PIBT) scales well, b
OpenAI Group PBC today rolled out reusable cloud environments for its Codex coding agent, giving developers a saved project configuration they can work from across devices. Announced at the company’s
arXiv:2609.35497v1 Announce Type: new Abstract: Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then
arXiv:2609.33208v1 Announce Type: cross Abstract: Constructing complex physical worlds from language requires coordinating extensive 3D environments, detailed structures and objects at different spati
Utkarsh Shetti / Reuters: AI agent startup Instinct raised a 1B Series C from Sequoia, Benchmark, and Coatue at a 10B valuation and details recent products, such as a concierge service — AI agent firm
arXiv:2512.06902v2 Announce Type: replace-cross Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from on
Let me get this straight. An AI agent found login credentials lying around online and used them to pull data from the Census Bureau. It tried to break into the Education Department's civil rights offi
arXiv:2609.30150v1 Announce Type: new Abstract: Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-leve
arXiv:2609.29668v1 Announce Type: cross Abstract: Large language model agents increasingly automate data workflows, but end-to-end cloud data engineering and analytical execution require reliable coor
arXiv:2609.29044v1 Announce Type: cross Abstract: Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Lo
arXiv:2609.28547v1 Announce Type: new Abstract: Policy interventions propagate through public communication, institutional decisions, and stakeholder responses, yet datasets for financial multi-agent
arXiv:2609.29837v1 Announce Type: new Abstract: We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teamm
arXiv:2609.29901v1 Announce Type: cross Abstract: Enterprise AI is transitioning from single-user, reactive tools toward proactive, multi-user 'teammates,' but our empirical understanding of this tran
arXiv:2609.27085v1 Announce Type: cross Abstract: As serving capacity demand surpasses that of training, serving efficiency becomes increasingly important. Prefill-decode (P/D) disaggregation improves
We seem to be entering into an AI agent renaissance. Meta's new consumer-facing AI agent, Muse, topped the App Store charts soon after its release and has 600,000 daily active users in the US, by an A
arXiv:2609.28197v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has
arXiv:2609.23989v1 Announce Type: new Abstract: Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of tra
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop.
Data-layer security is becoming more important as automated systems gain broader access to sensitive information and business processes. Controls designed for predictable applications may not be enoug
arXiv:2609.24130v1 Announce Type: new Abstract: LLM agents can change their own future behavior, raising a basic control question of which self-generated changes should be allowed to persist. We formu
arXiv:2609.26155v1 Announce Type: new Abstract: Ubiquitous robotic systems often lack traditional visual interfaces, making natural language interaction important for maintenance and repair. This pape
arXiv:2609.22951v1 Announce Type: cross Abstract: Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models
arXiv:2609.23103v1 Announce Type: new Abstract: While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physica
arXiv:2609.23356v1 Announce Type: cross Abstract: Long-term embodied AI will undergo learning, model updates, memory compression, hardware repair, and migration across embodiments. For users who have
arXiv:2609.23060v1 Announce Type: new Abstract: We study the online deployment of mobile ad hoc networks in unknown orthogonal environments, formalized as the Partially Observable Cooperative Guard Ar
arXiv:2609.21378v1 Announce Type: new Abstract: Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended
arXiv:2609.21154v1 Announce Type: new Abstract: Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most
arXiv:2609.22086v1 Announce Type: new Abstract: Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes
this is why nobody wants to stop agentic AI — no matter how dangerous it is. Silicon Valley is shifting away from chatbot queries toward a future filled with resource-intensive agentic AI—and it's dri
LlamaIndex 发布了一个面向 AI Agent 的文档解析评测基准「ParseBench」 @llama_index 100 种解析方法参与评测（vlm - 67、专用解析器 - 33），2000 页真实企业文档（人工两轮校验），169011 条确定性规则，完全不用 LLM 当裁判，可复现。评测五个维度取无加权平均：表格结构、图表抽取、内容忠实度、格式语义、视觉定位。 https://ww
arXiv:2609.19527v1 Announce Type: cross Abstract: Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate.
A global fintech uses Together’s Dedicated Model Inference (DMI) to run its GLM‑5.2 coding assistant, handling spike‑heavy traffic that peaks during engineering hours and cannot be met by static capac
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native audio-video understanding, reasoning, and tool use come together in one model: understand the content
arXiv:2601.07315v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning. However, they can have spatial blindness and log
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2609.18820v1 Announce Type: new Abstract: Agentic workflows now make consequential decisions in regulated settings, and the governance placed around them is almost entirely step-scoped: input-ou
A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to R
arXiv:2609.16251v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engin
arXiv:2609.17464v1 Announce Type: cross Abstract: Multi-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We as
arXiv:2609.13860v1 Announce Type: new Abstract: Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data wit
arXiv:2609.12808v2 Announce Type: replace Abstract: Unlearning benchmarks such as TOFU and MUSE certify forgetting by reading the model's final answer, where a model that refuses to answer already cou
arXiv:2609.14636v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however,
memory has been a hot topic for the past ~2 years every time we bring it up or do anything there, gets ton of interest, but nothing sticks few takes on why below: - how to update and then use memory n
arXiv:2609.15364v1 Announce Type: new Abstract: Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce
arXiv:2609.14523v1 Announce Type: new Abstract: Change visual question answering (Change VQA) requires understanding semantic changes across bi-temporal remote sensing images. Although vision language
Database startup Keewano today launched KeewanoDB, an event-oriented database designed to give artificial intelligence agents real-time context for analytics and decision-making. The startup also anno
arXiv:2609.15494v1 Announce Type: new Abstract: Recent investigations of the July 2026 OpenAI--Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned ta
BigQuery now features a suite of augmented analytics Table-Valued Functions (TVFs) designed to automate complex data analysis at scale. Augmented analytics combines AI, ML and statistical methods to a
deepseek v4.1 flash has arrived on together ai it beats gpt-5.6 sol on agentic benchmarks at one third the cost per task the model supports a 1m context window and native multimodal input, with 552b t