Goal Recognition (GR) is the task of inferring an agent's intended goal from partial observations of its behavior, typically in an online and one-shot setting. Despite recent advances in model-free GR, particularly in applications such as human-robot interaction, surveillance, and assistive systems, the field remains fragmented due to inconsistencies in benchmarks, domains, and evaluation protocols. To address this, we introduce gr-libs (https://github.com/MatanShamir1/gr_libs) and gr-envs (https://github.com/MatanShamir1/gr_envs), two complementary open-source frameworks that support the development, evaluation, and comparison of GR algorithms in Gym-compatible environments. gr-libs includes modular implementations of MDP-based GR baselines, diagnostic tools, and evaluation utilities. gr-envs provides a curated suite of environments adapted for dynamic and goal-directed behavior, along with wrappers that ensure compatibility with standard reinforcement learning toolkits. Together, these libraries offer a standardized, extensible, and reproducible platform for advancing GR research. Both packages are open-source and available on GitHub and PyPI.

The next time you get on a Zoom call, you might want to ask the person you're speaking with to push their finger into the side of their nose. Or maybe turn in complete profile to the camera for a minute. Those are just some of the methods experts have recommended as ways to provide assurance that you are seeing a real image of the person you are speaking to and not an impersonation created with deepfake technology. It sounds like a strange precaution, but we live in strange times. Last month, a top executive of the cryptocurrency exchange Binance said that fraudsters had used a sophisticated deepfake "hologram" of him to scam several cryptocurrency projects.

Plan recognition is one of the fundamental problems of AI, applicable to many domains, from user interfaces to cyber security. We focus on a class of algorithms that use plan libraries as input to the recognition process. Despite the prevalence of these approaches, they lack a standard representation, and have not been compared to each other on common test bed. This paper directly addresses this gap by providing a standard plan library representation and evaluation criteria to consider. Our representation is comprehensive enough to describe a variety of known plan recognition problems, yet it can be easily applied to existing algorithms, which can be evaluated using our defined criteria. We demonstrate this technique on two known algorithms, SBR and PHATT. We provide meaningful insights both about the differences and abilities of the algorithms. We show that SBR is superior to PHATT both in terms of computation time and space, but at the expense of functionality and compact representation. We also show that depth is the single feature of a plan library that increases the complexity of the recognition, regardless of the algorithm used.

Farmers around the world are facing the urgent question of how to sustainably feed a global population expected to reach 9.7 billion by 2050 -- and the answer, in part, might be found nestled among the cornstalks and soybeans on a farm a short distance from Washington, D.C. The fields are outfitted with a network of high-tech sensors that could revolutionize how food is grown across the globe by putting data in the hands of farmers and scientists in ways unimaginable a few years ago. The sensors are part of a groundbreaking new partnership between Microsoft and the U.S. Department of Agriculture (USDA). The 7,000-acre farm at the USDA's Beltsville Agricultural Research Center in Maryland is using FarmBeats, a project that aims to harness data and artificial intelligence to help farmers cut costs, increase yields and sustainably grow crops that are more resilient to climate change. "We can't simply double our acreage to produce this food," says Dan Roberts, research leader at the Sustainable Agricultural Systems Research Laboratory, located at the Beltsville center.