Large Language Models (LLMs) have shown remarkable reasoning capabilities on complex tasks, but they still suffer from out-of-date knowledge, hallucinations, and opaque decision-making. In contrast, Knowledge Graphs (KGs) can provide explicit and editable knowledge for LLMs to alleviate these issues. Existing paradigm of KG-augmented LLM manually predefines the breadth of exploration space and requires flawless navigation in KGs. However, this paradigm cannot adaptively explore reasoning paths in KGs based on the question semantics and self-correct erroneous reasoning paths, resulting in a bottleneck in efficiency and effect. To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer. Specifically, three important mechanisms of Guidance, Memory, and Reflection are designed to work together, to guarantee the adaptive breadth of self-correcting planning for graph reasoning. Finally, extensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of PoG.

Large Language Models (LLMs) have shown remarkable reasoning capabilities on complex tasks, but they still suffer from out-of-date knowledge, hallucinations, and opaque decision-making. In contrast, Knowledge Graphs (KGs) can provide explicit and editable knowledge for LLMs to alleviate these issues. Existing paradigm of KG-augmented LLM manually predefines the breadth of exploration space and requires flawless navigation in KGs. However, this paradigm cannot adaptively explore reasoning paths in KGs based on the question semantics and self-correct erroneous reasoning paths, resulting in a bottleneck in efficiency and effect. To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer. Specifically, three important mechanisms of Guidance, Memory, and Reflection are designed to work together, to guarantee the adaptive breadth of self-correcting planning for graph reasoning. Finally, extensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of PoG.

Accurate forecasting of electrical demand is essential for maintaining a stable and reliable power grid, optimizing the allocation of energy resources, and promoting efficient energy consumption practices. This study investigates the effectiveness of five hyperparameter optimization (HPO) algorithms -- Random Search, Covariance Matrix Adaptation Evolution Strategy (CMA--ES), Bayesian Optimization, Partial Swarm Optimization (PSO), and Nevergrad Optimizer (NGOpt) across univariate and multivariate Short-Term Load Forecasting (STLF) tasks. Using the Panama Electricity dataset (n=48,049), we evaluate HPO algorithms' performances on a surrogate forecasting algorithm, XGBoost, in terms of accuracy (i.e., MAPE, $R^2$) and runtime. Performance plots visualize these metrics across varying sample sizes from 1,000 to 20,000, and Kruskal--Wallis tests assess the statistical significance of the performance differences. Results reveal significant runtime advantages for HPO algorithms over Random Search. In univariate models, Bayesian optimization exhibited the lowest accuracy among the tested methods. This study provides valuable insights for optimizing XGBoost in the STLF context and identifies areas for future research.

The computer scientist and CEO who popularized the term'artificial general intelligence' (AGI) believes AI is verging on an exponential'intelligence explosion.' The PhD mathematician and futurist Ben Goertzel made the prediction while closing out a summit on AGI this month: 'It seems quite plausible we could get to human-level AGI within, let's say, the next three to eight years.' 'Once you get to human-level AGI,' Goertzel, sometimes called'father of AGI,' added, 'within a few years you could get a radically superhuman AGI.' While the futurist admitted that he'could be wrong,' he went on to predict that the only impediment to a runaway, ultra-advanced AI -- far more advanced than its human makers -- would be if the bot's'own conservatism' advised caution. Mathematician and futurist Ben Goertzel made the prediction while closing out a summit on AGI las week: 'we could get to human-level AGI within, let's say, the next three to eight years' Goertzel made his predictions during his closing remarks last week at the '2024 Beneficial AI Summit and Unconference,' partially sponsored by his own firm SingularityNET where he is CEO.

Google wants your help in preserving and restoring coral reefs, and has designed a platform to help with this mission in mere minutes. All you have to do is tune in. Called "Calling in Our Corals"(opens in a new tab), the new citizen science project is a collaboration between Google Arts and Culture and marine biologists across the globe. People are being asked to listen to underwater recordings of coral reefs in Marine Protected Areas through an online platform, identifying sounds made by fish, shrimp, and other marine creatures in order to monitor ecosystems and determine opportunities for reef restoration. Scientists have placed hydrophones in 10 reefs across Australia, Indonesia, Philippines, the U.S., Panama, and Sweden, which record 24 hours a day, meaning there's hundreds of hours to sift through.

The Mayflower Autonomous Ship finally arrived on the coast of Nova Scotia last month, marking the end of its long trek across the Atlantic. While the modern Mayflower is far from the first vessel to make that voyage, this small robotic boat is the largest to ever do so navigated by artificial intelligence with no humans aboard. A few technical hiccups notwithstanding, its trip is the latest evidence that the future of the high seas could be autonomous. Slowly, self-steering ships are becoming a reality. In Norway, an autonomous battery-powered container vessel is shuttling fertilizer between a factory and a local port, and pending a successful trial, it could be fully certified within the next two years.

Avikus, a subsidiary of Hyundai, has successfully completed the first transoceanic voyage of a large merchant ship using autonomous navigation technologies, the company said in a press release. With the increase in computational capabilities, autonomous navigation solutions are being tested in various fields of transportation. Autonomous cars are expected to bring in a new era of human transportation, and the maritime industry is also not very far behind. Last year, we reported on a fertilizer company that deployed a fully electric and autonomous container ship in Norway to save 40,000 truck trips every year. While this deployment was over a short distance, maritime transportation involves crossing oceans and often in very congested port areas.

As a result, companies have gone through a decade's worth of digital transformation in just a matter of months, with the pandemic forcing them to refresh archaic processes with AI, machine learning, and data science technologies. Such technological advancements will continue to evolve and further establish themselves as a critical component to managing complex logistical landscapes – from improving efficiency and mitigating the effects of a global labour shortage, to identifying more robust and dependable ways to move commodities. In a world where uncertainty is the only certainty, AI-enabled order and inventory visibility across shipments will also be vital to'keep the wheels in motion.' Most importantly, to provide real-time updates on changes to arrival times and to identify potential disruptions before and as they occur. Take the recent congestion issues at the Port of Los Angeles, for example.

Using artificial intelligence for rapid data collection and integration of shrunk the commander's decision cycle from days to minutes in some instances in a recent information experiment by U.S. Northern Command, the head of NORTHCOM said Wednesday. Speaking to reporters at the Pentagon, Gen. Glen VanHerck said the Global Information Dominance Exercise or GIDE, "focused a lot on contested logistics to give us a scenario where maybe a line of communication such as the Panama Canal may be challenged," by a peer competitor such as China or Russia. The experiment wrapped up during the second week of July. The experiment was hosted by NORTHCOM but included 11 combatant commands, which illustrated how they can integrate and act on data from satellites, planes, and other sources. It also tested the command's ability to use new artificial intelligence abilities to monitor and predict potential threats using those data sources.

For a glimpse of the power of sexual selection, the dance of the golden-collared manakin is hard to beat. Each June in the rainforests of Panama, the sparrow-size male birds gather to fluff their brilliant yellow throats, lift their wings, and clap them together in rapid fire, up to 60 times a second. When a female favors a male with her attention, he follows up with acrobatic leaps, more wing snaps, and perhaps a split-second, twisting backflip. “If manakins were human, they would be among the greatest artists, athletes, and socialites in our society,” says Ignacio Moore, an integrative organismal biologist at Virginia Polytechnic Institute and State University. As biologists have understood since Charles Darwin, such exhibitionism evolves when females choose to mate with males that have the most extravagant appearances and displays—a proxy for fitness. And now, by studying the genomes of the golden-collared manakin ( Manacus vitellinus ) and its relatives, researchers are exploring the genes that drive these elaborate behaviors and traits. Last month at the virtual meeting of the Society for Integrative and Comparative Biology, Moore and other researchers introduced four manakin genomes, adding to two already published, and singled out genes at work in the birds' muscles and brains that may make the displays possible. The work offers “a better understanding of why manakins do all the amazing things that they do,” says Emily DuVal, a behavioral ecologist at Florida State University. Over the past decade, researchers have learned much about how natural selection affects genomes. “In contrast, we know very little about the underlying basis of sexually selected traits,” says Christopher Balakrishnan, an evolutionary biologist at East Carolina University (ECU). By mapping traits and genes onto the manakin family tree, researchers are beginning to trace the stepwise genetic changes that led to the most elaborate displays and determine whether sexual selection works differently from natural selection. Other species—birds of paradise and bowerbirds, in particular—also mount impressive sexual displays. But manakins have a greater variety of such traits and, being more abundant and more accessible, are easier to study in-depth. We can “assess the genomic basis for these behaviors in a way that isn't possible for many other complex behavioral traits in vertebrates,” says Morgan Wirthlin, an evolutionary neurobiologist at Carnegie Mellon University. As Balakrishnan and his colleagues reported at the meeting, a sweet tooth—or beak—may have set the stage for sexual selection in manakins. Their ancestors are known to have switched their diet from insects to fruit, and researchers suspected the change to a more available and abundant food source gave males extra energy for procuring mates. By comparing genomes of manakin relatives that continue to eat insects with those of fruit-eating manakins, Balakrishnan, Maude Baldwin from the Max Planck Institute for Ornithology, and colleagues found evidence that fruit eating and elaborate male displays evolved in steps. The researchers learned that the genes coding for a savory taste receptor began to change even before manakins became fruit eaters. By the time the saffron-crested tyrant-manakin ( Neopelma chrysocephalum ) evolved, Baldwin reported at the meeting, the receptor had become sensitive to the sweetness of ripe fruits—a trait rare among birds. That species courts with simple hops—partway to the elaborate displays of the fruit-eating species that evolved later. Wirthlin and others explored the DNA that changed to make those behaviors possible. In her analysis of five manakin genomes, she focused on ultraconserved noncoding elements, segments of DNA that have stayed almost exactly the same across animals ranging from chickens to humans and are thought to play a crucial role in regulating other genes. Given this conservation, she thought they'd be a good place to look for possible fingerprints of sexual selection. In the manakin genomes, 57 elements showed slight differences from the matching sequences in other species; those changes might alter the activity of the genes they regulate. Some of those elements are clustered around genes for muscle proteins and hormone receptors and some are near genes expressed in the brain, including two, TLE4 and MEIS2 , active in a region needed for fast visual processing. Both genes are less active in manakins than in zebra finches, Wirthlin reported—a change that might help male manakins cope with the visual demands of their frenetic dances. Matthew Fuxjager, an integrative biologist at Brown University, is excited about Wirthlin's finding that evolution may have revved up the activity of genes for the birds' hormone receptors. The high-speed wing clapping in some species requires extra fast and powerful wing pectoral muscles—which are highly sensitive to the male hormone androgen. “Androgens are what dial up the speed,” by changing the activity of muscle performance genes, Fuxjager says. At the meeting, Balakrishnan reported pinpointing other genes that may also have supercharged those crucial muscles. His genomic analysis suggested that the activity of genes involved in muscle metabolism and growth changed early in manakin evolution, yielding more powerful muscles. He has not looked in females, but he and Fuxjager think the demands of flight, not mating, may have driven those early changes. Then, as sexual selection began to act on later-evolving species, changes in the androgen receptors and other signaling paths made the flight muscles in males capable of the very fast movements needed for the courtship displays. (Other research shows female muscles are not as sensitive to androgens.) The manakins' performance involves more than sound and movement—in some species it's a social act as well, coordinated among as many as 20 males. In all vertebrates, a network of brain “nuclei”—clusters of similar nerve cells—helps control social behavior, and studies presented at the meeting show the pattern of gene activity in those nuclei varies with testosterone levels. The work, by evolutionary biologist Peri Bolton at ECU and ecologists Brent Horton at Millersville University and Brent Ryder at the Smithsonian National Zoological Park, suggests changes in androgen receptors could have aided the birds' social sophistication as well as their athleticism. Dazzling as the manakins' displays are, researchers are just as awed by their intricate genetic underpinnings. “Our studies are teaching us that beauty is more than skin deep,” Moore says.