In a windowless shack on the far outskirts of Fresno, an ominious red glow illuminates a lab filled with X-ray machines, shelves of glowing boxes, a quietly humming incubator and a miniature wind tunnel. While the scene looks like something straight out of a sci-fi movie, its actually part of an experimental program to prevent a damaging almond pest from successfully mating. With California almond growers reeling from dropping nut prices and rising costs, the pests have only added to their woes. Every year, the navel orangeworm eats through roughly 2% of California's almonds before they can make it to grocery store shelves. Last year, it was almost double that.

Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group discussion framework to enrich the set of discussion mechanisms. Interestingly, our results show that a single-agent LLM with strong prompts can achieve almost the same performance as the best existing discussion approach on a wide range of reasoning tasks and backbone LLMs. We observe that the multi-agent discussion performs better than a single agent only when there is no demonstration in the prompt. Further study reveals the common interaction mechanisms of LLMs during the discussion.

Navigation of male moths toward females during the mating search offers a unique perspective on the exploration-exploitation (EE) model in decision-making. This study uses the EE model to explain male moth pheromone-driven flight paths. We leverage wind tunnel measurements and 3D tracking using infrared cameras to gain insights into male moth behavior. During the experiments in the wind tunnel, we add disturbance to the airflow and analyze the effect of increased fluctuations on moth flights in the context of the proposed EE model. We separate the exploration and exploitation phases by applying a genetic algorithm to the dataset of moth 3D trajectories. First, we demonstrate that the exploration-to-exploitation rate (EER) increases with distance from the source of the female pheromone, which can be explained in the context of the EE model. Furthermore, our findings reveal a compelling relationship between EER and increased flow fluctuations near the pheromone source. Using the open-source pheromone plume simulation and our moth-inspired navigation model, we explain why male moths exhibit an enhanced EER as turbulence levels increase, emphasizing the agent's adaptation to dynamically changing environments. This research extends our understanding of optimal navigation strategies based on general biological EE models and supports the development of advanced, theoretically supported bio-inspired navigation algorithms. We provide important insights into the potential of bio-inspired navigation models for addressing complex decision-making challenges.

When we look at the world around us, we sometimes wonder how everything we see and interact with came to be. One way to explain this is the theory of evolution. The theory of evolution suggests that the living organisms that we see today did not suddenly exist that way, but evolved through millions of years of subtle changes, with each generation adapting to its environment. This implies that the physical and cognitive characteristics of each living organism are a result of best fitting to its environment for survival. Organisms evolve through reproduction by producing children of mixed genes from their parents.

Dutch cress grower Rob Baan has enlisted high-tech helpers to tackle a pest in his greenhouses: palm-sized drones seek and destroy moths that produce caterpillars that can chew up his crops. "I have unique products where you don't get certification to spray chemicals and I don't want it," Baan said in an interview in a greenhouse bathed in the pink glow of LED lights that help his seedlings grow. His company, Koppert Cress, exports aromatic seedlings, plants and flowers to top-end restaurants around the world. A keen adopter of innovative technology in his greenhouses, Baan turned to PATS Indoor Drone Solutions, a startup that is developing autonomous drone systems as greenhouse sentinels, to add another layer of protection for his plants. The drones themselves are basic, but they are steered by smart technology aided by special cameras that scan the airspace in greenhouses.

Researchers at the University of Washington have developed a tiny new sensor that can be carried around on a small drone or even the back of an insect – and then dropped on demand to track the environment for years at a time. Obviously there are a few main features that this kind of system needs. The sensor needs to be very lightweight, it needs to be securely attached to its transport until a "drop" command is issued, then it needs to be able to survive a fall from a high place, and finally it has to be able to run for a decent amount of time. The team addressed all of those points with the design. The whole sensor system weighs just 98 milligrams, which they describe as about one 10th the weight of a jellybean.

The flight patterns of moths could help scientists to develop decision-making programs for autonomous drones to help them navigate unfamiliar environments. Researchers led from Washington State in the US analysed how moths flew through a simulated forest of light beams to create a drone navigation model to test. They found that the moths' navigation strategy is highly flexible and best suited for dense forests -- an adaptation that likely evolved in response to their habitat. By using real data from animal flight paths, the researchers said that they should be able to program drones to autonomously navigate cluttered environments. Biologist Thomas Daniel of the University of Washington in Seattle and colleagues mounted eight tobacco hawk moths -- or Mantuca sexta -- on the end of metal rods that were connected to a torque meter.

Despite many successes, machine learning (ML) methods such as neural nets often struggle to learn given small training sets. In contrast, biological neural nets (BNNs) excel at fast learning. We can thus look to BNNs for tools to improve performance of ML methods in this low-data regime. The insect olfactory network, though simple, can learn new odors very rapidly. Its two key structures are a layer with competitive inhibition (the Antennal Lobe, AL), followed by a high dimensional sparse plastic layer (the Mushroom Body, MB). This AL-MB network can rapidly learn not only odors but also handwritten digits, better in fact than standard ML methods in the few-shot regime. In this work, we deploy the AL-MB network as an automatic feature generator, using its Readout Neurons as additional features for standard ML classifiers. We hypothesize that the AL-MB structure has a strong intrinsic clustering ability; and that its Readout Neurons, used as input features, will boost the performance of ML methods. We find that these "insect cyborgs", ie classifiers that are part-moth and part-ML method, deliver significantly better performance than baseline ML methods alone on a generic (non-spatial) 85-feature, 10-class task derived from the MNIST dataset. Accuracy improves by an average of 6% to 33% for N < 15 training samples per class, and by 6% to 10% for N > 15. Remarkably, these moth-generated features increase ML accuracy even when the ML method's baseline accuracy already exceeds the AL-MB's own limited capacity. The two structures in the AL-MB, a competitive inhibition layer and a high-dimensional sparse layer with Hebbian plasticity, are novel in the context of artificial NNs but endemic in BNNs. We believe they can be deployed either prepended as feature generators or inserted as layers into deep NNs, to potentially improve ML performance.

The olfactory learning system in moths is relatively simple and well mapped by neuroscientists. It consists of five distinct networks that feed information forward from one to the next. The first is a system of around 30,000 chemical receptors that detect odors and send a rather noisy set of signals to the next level, known as the antenna lobe. This contains about 60 units, known as glomeruli, that each focus on specific odors. The antenna lobe then sends neural odor codes to the mushroom body, which contains some 4,000 kenyon cells and is thought to encode odors as memories.

Prime Minister Narendra Modi on Sunday said that with Artificial Intelligence (AI), bots and robots, productivity will increase, but warned of rising apprehensions of'human redundancy' as the mind and machines would compete directly. For avoiding this scenario, he urged that AI should be Made in India and Made to Work for India and asked the students and teachers to identify the grand challenges facing the country that can be resolved by applications of AI....