Agents & autonomy

simonw/pedalican Clearly I wasn't paying attention when these were first announced back in May, but today I accidentally activated a "pet" in Codex Desktop - a little animated robot, reminiscent of Clippy - and then learned you can create your own. So I did, and now I have a cute little pelican on a bicycle bouncing around my desktop giving me updates on my Codex tasks. Your browser does not support HTML5 video. The most interesting thing about this process was watching how the custom pet was cr

Surgeons remotely control two human-like robots in an operating theatre.

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual d

OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience. To resolve these issues, we propose the Know Deeply, Act Perfectly paradigm for personal assistants, which holds that accumulated user interaction and task-run

As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely B

Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination. Unlike vision-language models that emphasize scene understanding and textual decision making, or generative world models that mainly predict future visual states, RxBrain represents embodied plans in a single planning sequence where language and visual imagina

Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited. A healthcare model must handle patient consultation, clinical reasoning over text and images, interactive diagnosis, and electronic health record (EHR) tool use. These capabilities fail in different ways, and a narrow update for one task can degrade another. We present Cura 1T, a healthcare-specialized LLM trained through a human-gated sel

Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, community-oriented egocentric manipulation dataset and toolchain spanning the full pipeline from smartphone capture to model training. Its first release contains approximately 2,000 hours of manipulation video collected in na

Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledg

Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, does not prevent this; it applies language and action losses to separate observations, leaving VLAs with language-action misalignment that stan

Large language models are increasingly deployed as agents, but reliable agentic behavior requires more than next-token prediction. At inference time, it is preferred that an agent can decide whether to proceed with its current reasoning, defer to a stronger model, request additional information, invoke external tools, or abstain under the given setup. Existing approaches address these decisions through prompt-level routing, external orchestration, or task-specific fine-tuning, which primarily re

Agentic AI introduces new insurance challenges because autonomous AI systems can make decisions, invoke tools, modify external environments, and interact with third-party services. This paper develops an AI-native mathematical framework for underwriting, pricing, and contract design for agentic AI deployments. A deployment is represented by a risk state that captures autonomy level, operational authority, permission exposure, governance maturity, and dependency concentration. The framework maps

Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, or digital co-scientists working with one principal user. However, challenging scientific problems are rarely solved by one reasoner alone. They are solved by teams whose members bring different priors, experimental backgrounds, tacit knowledge, and domain-trained intuitions. The open problem is therefore not only how to scale models, but how to c

Logistics company C.H. Robinson has seen a 45% productivity gain from deploying AI agents. Its CEO Dave Bozeman explains how he's found ROI from AI.

Providing secure access for your human staff is no simple task. For one, traditional VPNs often grant unnecessarily broad access, The post What happens when your VPN meets 200 AI agents appeared first on The New Stack .

The pause follows deadly shootings in Houston and Maine involving agents shooting into vehicles

User Experience (UX) is recognized as a critical factor for the success of digital products, particularly in software startups, environments marked by time constraints, limited resources, and low maturity in design practices. Building Minimum Viable Products (MVPs) through low-fidelity prototyping represents a well-established strategy for rapid validation cycles at reduced cost. A systematic literature mapping, however, revealed gaps in the ecosystem of available tools: a predominance of genera

The shared language of a software project is not English or Python but it is the common understanding of what its concepts mean, where the boundaries are, which invariants matter, who owns what, and why the system has the shape it does. This language is rarely written down in one place. It lives partly in documentation and code, but also in code review, conversations, arguments, and the experience of having to explain a change to somebody else. Before agents, some of this shared understanding wa

Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the information it truly needs, and the shortest reliable path be

Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains. We present TerraZero, a procedural driving simulator and self-play training stack. A configurable C engine runs simulation on the CPU and policy inference on the GPU over a zero-copy path, sustaining 1.3M agent-steps per se

Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most agent systems run on desktops or servers, which support tool use and task automation. Mobile devices are also important agent environments because they are widely accessible and contain users' data, sensors, and daily-use applications. Existing mobile agents mainly operate smartphones through graphical user

A hot action movie package is coming together at Netflix, multiple sources told Variety, one roughly 33 years in the making. “Reacher” and “War Machine” star Alan Ritchson is in negotiations to topline “Maelstrom,” a spec originally sold to Warner Bros. in 1993 by prolific producer Jeff Robinov when he was an agent. Jaume Collet-Serra, helmer […]

Richard Sutton gründet „Oak Lab“. Das Startup will KI-Agenten bauen, die im laufenden Betrieb lernen – statt nach dem Training statisch zu bleiben.

Publication date: September 2026 Source: Artificial Intelligence, Volume 358 Author(s): Yihao Liu, Xueyan Tang, Wentong Cai, Jingning Li

Publication date: September 2026 Source: Technology in Society, Volume 88 Author(s): Brahim Bergougui

Publication date: September 2026 Source: Telecommunications Policy, Volume 50, Issue 8 Author(s): Mengxuan Wu, Weiwei Zheng, Wei Wang

Publication date: September 2026 Source: Technology in Society, Volume 88 Author(s): Ylenia Curzi, Tiziana C. Callari, Niels Lohse

Publication date: September 2026 Source: Technology in Society, Volume 88 Author(s): Ricarda B. Bouncken, Beate Cesinger

Publication date: September 2026 Source: Futures, Volume 182 Author(s): Manal Ahdadou

Publication date: October–November 2026 Source: International Journal of Human-Computer Studies, Volume 215 Author(s): Min Cai, Kuangyong Gao, Ziling Ji, Xueqi Xu

Publication date: October–November 2026 Source: International Journal of Human-Computer Studies, Volume 215 Author(s): Dawid Ratajczyk, Zuzanna Kurowska, Aleksandra Wasielewska, Paweł Łupkowski

Publication date: November 2026 Source: Computers in Human Behavior, Volume 184 Author(s): Caihua Yu, Siwen Xu, Tonghui Lian

Publication date: November 2026 Source: Computers in Human Behavior, Volume 184 Author(s): Yunze Zhao, Mengting Lu

Publication date: November 2026 Source: Computers in Human Behavior, Volume 184 Author(s): Fu-Song Hsu, Wei-Ting Pai, I-Chia Tsai

Publication date: October–November 2026 Source: International Journal of Human-Computer Studies, Volume 215 Author(s): Davide Piras, Alberto Pes, Diego Reforgiato Recupero, Giuseppe Scarpi

Publication date: August–September 2026 Source: International Journal of Human-Computer Studies, Volume 214 Author(s): Gaurav Patil, Le Quynh Trang Pham, Patrick Nalepka, Rachel W. Kallen, Michael J. Richardson

Publication date: August 2026 Source: Technology in Society, Volume 87 Author(s): Susanne Frennert, Björn Fischer, Günter Alce

Publication date: October 2026 Source: Technological Forecasting and Social Change, Volume 231 Author(s): Nik Hynek, Beata Gavurova, Marinko Skare, Matus Kubak, Michal Senk

Publication date: December 2026 Source: Computers and Education: Artificial Intelligence, Volume 11 Author(s): Solomon Sunday Oyelere

Publication date: October 2026 Source: Technological Forecasting and Social Change, Volume 231 Author(s): Giovanni Guidetti, Riccardo Leoncini, Mariele Macaluso