Large language models (LLMs) often struggle when performing agentic tasks without substantial tool support, prom-pt engineering, or fine tuning. Despite research showing that domain-dependent, procedural knowledge can dramatically increase planning efficiency, little work evaluates its potential for improving LLM performance on agentic tasks that may require implicit planning. We formalize, implement, and evaluate an agentic LLM workflow that leverages procedural knowledge in the form of a hierarchical task network (HTN). Empirical results of our implementation show that hand-coded HTNs can dramatically improve LLM performance on agentic tasks, and using HTNs can boost a 20b or 70b parameter LLM to outperform a much larger 120b parameter LLM baseline. Furthermore, LLM-created HTNs improve overall performance, though less so. The results suggest that leveraging expertise--from humans, documents, or LLMs--to curate procedural knowledge will become another important tool for improving LLM workflows.

Drone teams competing for points under the'Army of Drones Bonus System' killed or wounded 18,000 Russian soldiers in September. Drone teams competing for points under the'Army of Drones Bonus System' killed or wounded 18,000 Russian soldiers in September. Ukrainian computer game-style drone attack system goes'viral' A computer game-style drone attack system has gone "viral" among Ukrainian military units and is being extended to reconnaissance, artillery and logistics operations, the nation's first deputy prime minister, Mykhailo Fedorov, has told the Guardian. Drone teams competing for points under the "Army of Drones Bonus System" killed or wounded 18,000 Russian soldiers in September, with 400 drone units now taking part in the competition, up from 95 in August, Ukrainian officials said. The system, which launched more than a year ago, rewards soldiers who achieve strikes with points that can be exchanged to buy more weapons in an "Amazon-for-war" online store called Brave1 filled with more than 100 different drones, autonomous vehicles and other drone war material.

Some standardized environments have been designed for partially observable multi-agent cooperation, but we find most current environments are synchronous, whereas real-world agents often have their own action spaces leading to asynchrony. Furthermore, fixed agents number limits the scalability of action space, whereas in reality agents number can change resulting in a flexible action space. In addition, current environments are balanced, which is not always the case in the real world where there may be an ability gap between different parties leading to asymmetry. Finally, current environments tend to have less stochasticity with simple state transitions, whereas real-world environments can be highly stochastic and result in extremely risky. To address this gap, we propose WarGame Challenge (WGC) inspired by the Wargame. WGC is a lightweight, flexible, and easy-to-use environment with a clear framework that can be easily configured by users. Along with the benchmark, we provide MARL baseline algorithms such as QMIX and a toolkit to help algorithms complete performance tests on WGC. Finally, we present baseline experiment results, which demonstrate the challenges of WGC. We think WGC enrichs the partially observable multi-agent cooperation domain and introduces more challenges that better reflect the real-world characteristics. Code is release in http://turingai.ia.ac.cn/data\_center/show/10.

In the east Ukrainian city of Bakhmut, 15 kilometres (nine miles) from the positions held by Russian forces, an artillery unit waits for the signal. The four soldiers duck and put their hands over their ears. "According to the coordinates we received, the target is infantry," says Oleksandr, 37, between two radioed orders. Around 30 seconds later, the 50 kilo (110-pound) "fragmentation" shell, pinched from the Russians after their retreat from a nearby town, will explode above the position held by Moscow's troops, showering them with its payload. A Ukrainian drone supports the operation "in real time", monitoring the effectiveness of the strike from the old Soviet D-20 cannon in order to better calibrate the next one.

A task force focused on soldier lethality is adding new initiatives to its portfolio, including a lighter Javelin missile, identifying how artificial intelligence can help squads, and looking into robot dogs as infantry battle buddies. The Close Combat Lethality Task Force, established in 2018 under then-Secretary of Defense Jim Mattis, pushed for the Next Generation Squad Weapon, a 6.8mm intermediate-caliber replacement for the M4 for close combat troops, which was selected this year and begins fielding to troops in 2023. It also lobbied for additional funding and prioritization for the Integrated Visual Augmentation System, a $22 billion program for a mixed-reality goggle aimed to put fighter pilot situational awareness tools in the view of squad-level soldiers. On the human side, the task force supported efforts to revitalize infantry and close-combat training, increase unit cohesion by keeping infantry troops in the field longer, and reduce training tasks not related to combat. But the task force has mostly remained in the shadows and sought a home since Mattis left office in 2019.

The People's Republic of China recently published a "position paper" detailing the nation's views on military AI regulation. Having thoroughly perused it, we've come to the following conclusion: it's gibberish. Up front: The first thing you want to know when a global superpower releases official government documentation detailing its views on the use of artificial intelligence for military applications is whether the signatory intends to develop lethal autonomous weapons systems (LAWS). China's position paper makes absolutely no mention of restricting the use of machines capable of choosing and firing on targets autonomously. Tickets to TNW 2022 are available now!

From the author: "Loose Ends" is a literary supercut composed entirely of last lines from 137 science fiction and fantasy books. After gathering these lines, I found they fell into a number of patterns--some surprising, others obvious--in how writers end their stories. With these patterns in hand, I arranged them into a sequence of interconnected vignettes. In these ways "Loose Ends" doubles as narrative and archive, short story and data analysis. To read a version that reveals the names of the books, click here.

It has become clear, in these last decades of decadence, decline, towering institutional violence, and rampant bad taste, that American life is stuck somewhere inside the Paul Verhoeven cinematic universe. In the bloody, satirical sci-fi films that made his name with American audiences, Verhoeven dealt in a singularly unappealing vision of the future, one both luridly inventive and careful about where not to be imaginative. "RoboCop," from 1987, set in a futuristic Detroit, is a gleeful exaggeration of the anxieties of Reagan-era urban life: the office towers are even more isolated, and their boardrooms more brazenly sociopathic; the popular culture is a tick or two more savage and leering; the police are more overmatched and the streets more ungovernable. "Total Recall," released in 1990 and adapted from a short story by Philip K. Dick, does feature humans living on Mars, a private company that implants bespoke memories in its clients, and a brassy three-breasted space prostitute, but its vision of 2084 is in other respects familiar. Mars is dirty, violent, and unequal, and the colony is overseen by the private security force of a capitalist who has staked out a monopoly on oxygen itself.

Infantry Soldiers with 1st Battalion, 8th Infantry Regiment, 3rd Armored Brigade Combat Team, 4th Infantry Division, fire an FGM-148 Javelin during a combined arms live fire exercise in Jordan on August 27, 2019, in support of Eager Lion - file photo. A small group of maneuvering infantry soldiers will soon be able to target and destroy enemy tanks at night from distances up to 4.5 kilometers (2.8 miles) -- by firing portable, man-carried Javelin Anti-Tank Missiles engineered with a new generation of targeting optics. The U.S. Army and Raytheon plan to enter production of a new Lightweight Command Launch Unit for the Javelin designed to bring a new level of "precision lethality to an infantry squad." The new Lightweight CLU unit enables much greater standoff distance for infantry attacking tanks by doubling the attack range from 2.5km to 4.5km, developers said. "You have to be able to speed up the kill chain and detect the adversary before he can detect you. You want to get a launch shot off before he knows you are there. It all starts with sensing," Tommy Boccardi, Javelin Domestic Business Development, Raytheon, told Warrior.

An army of'killer robots' that will assist infantry on the battlefield has been unveiled in propaganda footage released by Russia The video, released by the Kremlin, appears to showcase the state's latest drone technology. That includes and AI-controlled driverless tank that follow the aim of a soldier's rifle to obliterate targets with its own weaponry. Russia's Advanced Research Foundation (ARF) said the ultimate goal is to have an army of robots entirely controlled by Artificial Intelligence algorithms. Currently the drones are deployed alongside infantry who remotely control the vehicles, but in the future the tech will be fully autonomous. That means the military hardware will be able to target and kill enemies without any human intervention.