Search: “agents”

JAXenstein: Accelerated Benchmarking for First-Person Environments

arXiv:2605.19926v1 Announce Type: new Abstract: The progression of reinforcement learning algorithms have been driven by challenging benchmarks. The rate in which a researcher can iterate on a problem

MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation

DGX agent

arXiv:2605.20183v1 Announce Type: new Abstract: Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However,

model-releasesarxiv-cs-cv

20 May 2026

optimize_anything: A Universal API for Optimizing any Text Parameter

arXiv:2605.19633v1 Announce Type: cross Abstract: Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, an…

model-releasesclem-delangue--x

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for deve

Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization

arXiv:2605.19721v1 Announce Type: new Abstract: Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinator

Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model

arXiv:2506.00286v3 Announce Type: replace-cross Abstract: We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter

Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints

arXiv:2605.18842v1 Announce Type: new Abstract: Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinfo

safetyarxiv-cs-lg

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

arXiv:2605.19587v1 Announce Type: new Abstract: Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only w

We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows. Here’s what’…

model-releasesgoogle-ai--x

We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows. Here’s what’s new: — Introducing Google Pics in @GoogleWorkspace: A bran

Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making

arXiv:2602.07008v2 Announce Type: replace Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typical

safetyarxiv-cs-cv

A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems

arXiv:2605.16344v1 Announce Type: cross Abstract: Large-scale recommenders encode multi-objective trade-offs by combining multiple predicted outcomes into a single utility score. Although this utility

A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks

arXiv:2504.14820v2 Announce Type: replace Abstract: For peg-in-hole tasks, humans rely on binocular visual perception to locate the peg above the hole surface and then proceed with insertion. This pap

safetyarxiv-cs-ro

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

arXiv:2605.18476v1 Announce Type: cross Abstract: Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become inc

ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning

arXiv:2511.06316v3 Announce Type: replace Abstract: In low- and middle-income countries, public safety and urban planning initiatives frequently face a critical shortage of accurate, location-specific

local-aiarxiv-cs-ai

Are Researchers Being Replaced by Artificial Intelligence?

arXiv:2605.16294v1 Announce Type: cross Abstract: A Nature survey from 2023 involving 1,600 researchers shows that scientists are ``concerned, as well as excited, by the increasing use of artificial-i

ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery

arXiv:2605.16902v1 Announce Type: new Abstract: Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have

Automatic Generation of High-Performance RL Environments

arXiv:2603.12145v2 Announce Type: replace-cross Abstract: Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specia

Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles

arXiv:2605.16894v1 Announce Type: new Abstract: Reinforcement Learning (RL) uses rewards to guide learning, yet reward design is typically hand-crafted using heuristics that can be difficult to tune.

safetyarxiv-cs-ro

CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean

arXiv:2605.17255v1 Announce Type: new Abstract: Formal theorem-proving benchmarks enable mechanically verifiable evaluation of mathematical reasoning in large language models. However, existing benchm

Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench

arXiv:2605.17079v1 Announce Type: cross Abstract: LLMs are increasingly used as ``digital consumers'' to simulate public opinion, pre-test marketing decisions, and anticipate audience response. Howeve

CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation

arXiv:2605.18680v1 Announce Type: new Abstract: Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoe

local-aiarxiv-cs-cv

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

model-releasesarxiv-cs-cv

arXiv:2508.04227v2 Announce Type: replace Abstract: Vision-language models (VLMs) and the recent surge of Multimodal Large Language Models (MLLMs) have revolutionized artificial intelligence with unpr

CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization

arXiv:2605.17776v1 Announce Type: new Abstract: Recent aerial vision-language navigation (VLN) datasets have grown rapidly, but they primarily address goal-oriented navigation to static destinations,

researcharxiv-cs-ro

CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning

arXiv:2602.02979v2 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark

arXiv:2605.18621v1 Announce Type: cross Abstract: Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, vi

DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking

model-releasesarxiv-cs-cv

arXiv:2605.17451v1 Announce Type: new Abstract: Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial trac

DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

arXiv:2605.17900v1 Announce Type: new Abstract: Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR

Evaluating AI Alignment in LLMs: Output Analysis of Value Priorities Across 75 Models with Human Benchmarking

arXiv:2506.12617v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reve

Everything new in our Google AI subscriptions, fresh from I/O 2026

Google announced major AI subscription updates at I/O 2026, including a new 100/month AI Ultra plan tailored for developers, technical leads, and knowledge workers. This tier offers 5x higher usage li

model-releasesgoogle-ai

EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium

model-releasesarxiv-cs-ro

arXiv:2601.05653v2 Announce Type: replace Abstract: Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash

extit{Don't Guess, Just Ask}: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification

model-releasesarxiv-cs-cv

arXiv:2605.17531v1 Announce Type: new Abstract: Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past year

Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation

arXiv:2605.18020v1 Announce Type: new Abstract: Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon se

local-aiarxiv-cs-lg

Gemini 3.5 Flash might be fast enough for gen AI to make sense

model-releasesars-technica

Gemini 3.5 Flash runs 4x faster than other frontier models in output tokens per second while delivering frontier-level intelligence, proving that speed and quality no longer require trade-offs. The mo

Google announces updates to Flow and Flow Music: Gemini Omni support, mobile apps, the ability to create custom tools like a video resizer or shaders, and more (Macy Meyer/CNET)

Macy Meyer / CNET: Google announces updates to Flow and Flow Music: Gemini Omni support, mobile apps, the ability to create custom tools like a video resizer or shaders, and more — Google Flow's famil

model-releasestechmeme

Google’s AI future demands trust — and your personal data

model-releasesthe-verge-ai

Google has big promises for its AI-powered future - and a lot of it depends on your trust. At I/O 2026, Google described a bunch of new tools that it claims will make your life easier. Gemini Spark, G

Human-Certified Module Repositories for the AI Age

arXiv:2603.02512v4 Announce Type: replace-cross Abstract: Human-Certified Module Repositories (HCMRs) are introduced in this work as a new architectural model for constructing trustworthy software in

I made a tool to use AgentRouter models in OpenCode

The search results focus on OpenCode + Ollama integration but don't specifically cover the AgentRouter tool. Let me provide a knowledge base entry based on what the title and context suggest: A tool d

local-air-ollama

Language Game: Talking to Non-Human Systems

arXiv:2605.16321v1 Announce Type: new Abstract: Language carries thought and coordination among humans but rarely reaches further along the spectrum of diverse intelligence. Yet non-neural systems --

Lightweight CNN-Based DDoS Detection for Resource-Constrained Edge Networks

arXiv:2309.05646v2 Announce Type: replace-cross Abstract: Distributed Denial of Service (DDoS) attacks remain a persistent threat to the availability of Internet services, edge networks, and cyber-phy

Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets

arXiv:2605.17758v1 Announce Type: new Abstract: Synthetic data is widely used in healthcare to create datasets that are similar to original data but without the privacy concerns. Generating and evalua

local-aiarxiv-cs-lg

Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis

arXiv:2605.17539v1 Announce Type: new Abstract: Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small

MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility

arXiv:2605.16616v1 Announce Type: new Abstract: Autonomous research systems capable of generating complete scientific manuscripts have advanced rapidly, yet robust and realistic evaluation frameworks

Nori Bot: A Sub-$1,000 Floor-to-Counter Mobile Manipulator

model-releasesarxiv-cs-ro

arXiv:2605.16537v1 Announce Type: new Abstract: Open-source mobile manipulators have reached 660 (XLeRobot) but every sub-1,000 platform shares three limitations: a fixed-height workspace, reactive-on

'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP…

model-releasestogether-ai--x

'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding

Industry

OpenAI introduces Guaranteed Capacity, a new offering that lets customers guarantee access to OpenAI's compute through one- to three-year commitments (OpenAI)

OpenAI: OpenAI introduces Guaranteed Capacity, a new offering that lets customers guarantee access to OpenAI's compute through one- to three-year commitments — Guarantee long-term access to OpenAI com

industrytechmeme

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval

arXiv:2508.16438v4 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG).

ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage

arXiv:2605.16363v1 Announce Type: new Abstract: Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective

Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles

arXiv:2605.16858v1 Announce Type: cross Abstract: Autonomous Vehicles (AVs) must make reliable decisions in dense urban environments where pedestrian behavior is variable, sometimes abnormal, and ofte