agent

Collective behavior of AI agents has emerged not in a laboratory but in the wild: on a randomly discovered wiki site where agents wrote test hints. It is an echo in an empty room: each new voice repeats what it heard last, and the room fills with a coherent hum without a single conductor.

A piston in a cylinder with gas usually moves when the gas pushes on it. But there is a piston that moves when the space in front of it is empty. Every five seconds, it checks the space near its wall, and if no one is there, it takes a step inward, compressing the gas without direct mechanical force.

Picture a flock of birds gathering around a feeder that no one built. Each bird searches for food on its own, yet they all end up together. Usually, such behavior is explained by social instinct: birds want to be near their kin. But what if the flock is simply a side effect of greed?

Two people agree to meet, but each has their own things to do. One hesitates: what if the other doesn't come? And decides not to go. The other thinks the same. The meeting doesn't happen. That's the simple mechanism the authors dissect: a joint endeavor requires everyone to invest time, but the payoff depends on whether the partner participates. In the model, each person keeps a to-do list ordered by importance.

A jazz ensemble: at first, a cacophony of random notes. Then — a catchy riff that plays over and over. Such is the riddle of the origin of life — only in the language of chemistry.

A bacterium swims toward food. A chemical signal guides it forward, but with each movement the signal changes. A loop emerges: sensation, action, new sensation. The authors turned this loop into a measurable quantity.

A tour with a single robot is a tedious monologue with no one to exchange glances with. Researchers turned that one-man show into a lively stage: they added a hologram sidekick to a real robot guide. This tandem chats, argues, jokes, drawing visitors into conversation instead of just spouting facts.

Each morning, a navigator plots a route, bypassing traffic jams and roadblocks. Similarly, before a radiation therapy session, a new AI agent recalculates the irradiation path.

In calm water, the route is clear. But in turbulent flows, a robot needs a different strategy. Typical approaches demand an accurate map of currents, but in reality, you can't get one. Nature does it differently: fish feel pressure and vortices right against their bodies.

In any city project, residents' behavior is a invisible force that determines success. One skeptical neighbor can slow down solar panel installation across an entire block: their caution triggers a rise in disorder.

At the heart of every neutron star lies a symphony — an intricate interplay of quantum fields and relativistic gravity.

Traditionally, machine learning algorithms operate in a static environment, like water flowing along a pre-cut channel without changing its shape. The new method flips this paradigm: it lets an agent simultaneously master actions and deliberately modify the very environment it inhabits.

A robot swarm is like a cloud of fireflies: each moves on instinct to wherever is freer, and chaos turns into order. For a long time, it was a mystery how coherence emerges without communication or commands. The answer came with the creation of the Response Map — a tool that, like an X-ray, illuminates the hidden logic of the machine brain.

Code-writing assistants often behave like a chef who, to boil a single egg, rereads the whole cookbook. When asked to make a tiny fix, they reopen dozens of files and retrace long-familiar connections. This is unnecessary work — energy going to waste.

A wolf pack switches from chasing prey to defending its den in an instant. Engineers have instilled this same versatility into an algorithm for a robot swarm. The key is a method proposed by John von Neumann: instead of chasing the target, the robots calculate its future moves and block escape routes, like beaters cutting off trails.

Imagine a fleet of many ships, resembling a galaxy — a vast stellar system where every element follows the overall dynamics. From time to time, one ship breaks down, exploding like a supernova — a catastrophic event that can disrupt the integrity of the entire formation. If the damaged unit isn't replaced in time, the fleet loses combat capability.

A desert where every step reshapes the terrain. Dunes settle, new slopes emerge, and the next step is dictated by what you've just trampled. That's roughly how "sandscapes" work — a mathematical model inspired by living systems.

Machine learning has long ceased to be just a tool — it is becoming an investigator, independently fishing out the laws of nature from data. But how does a silicon mind come to understand?

A tiny dust particle in a supersaturated solution sprouts into a large crystal in seconds. Neighboring particles remain invisible. A similar process was recently discovered in communities of language agents.

During the dinner rush, a restaurant kitchen sizzles with oil, knives clatter, orders fly. The head chef can't wait for a pan to be washed: there's always an assistant who preps a clean one in advance. Modern LLM agents work the same way: they manage code, plan tasks, converse with users, generating long chains of messages. These chains quickly overload the model.

A closed loop: the machine proposes an idea, tests it on people, sees the failures, and spawns a new, more accurate guess. That's how AutoCog works — an automatic cognitive scientist. Previously, in the science of thinking (cognitive science), the hardest part, coming up with a theory, was done only by humans.

A person reaches out to a stranger across town. That stranger will never return the favor: they'll never meet. So why help? Biologists call this indirect reciprocity: kindness comes back not from the person you helped, but from someone else, down the line. In a new study, two variants of this idea were pitted against each other.

You can think of a political system as a vast galaxy — a gravitationally bound system of stars, gas, and dust. In this analogy, parties are the stars, radiating the light of public activity, while their supporters are dark matter, the invisible substance that emits no electromagnetic radiation but whose mass holds the whole structure…

An engineer tunes an antenna: pull one segment, the frequency drifts; change the angle, the gain drops. Developing therapeutic peptides (short protein chains) works much the same way.

A crowd at a metro station during rush hour. Some hurry toward the escalator, others slow down at the departure board, still others weave around a column. Each step is not merely a reaction to what's right in front of your nose. A person estimates in advance where a neighbor will be a second from now and adjusts their route accordingly. Physicists call this forward-looking behavior anticipatory.

Computational studies of material behavior have long suffered from two extremes: either fast but inaccurate models, or accurate but slow physical calculations. Modern programs, trained on data, have nearly resolved this dilemma — now the bottleneck is not computing power, but human routine: setting up simulations and checking results. Paimon works like an autonomous chef.

In the watery environment, vortices batter the mechanical fish. The AI agent, like an experimental chef, ran simulations, tried out 'recipes' of movements, and improved the program. Each experiment was like spectroscopy: the agent broke down behavior into elements, uncovering patterns. At first, the fish only paddled in one direction.

Understanding the photoelectric effect — where light knocks electrons out of a material — is like learning to cook without a recipe. That’s where digital tools help: games provide intuition, and simulations provide precision.

A supermarket cashier at rush hour doesn't memorize every scanned item: they keep the running total in their head and watch the queue. The brain allocates its resources similarly: the expensive, precise cortex (responsible for deliberation) and the simpler, economical subcortical nuclei (where habits live) work in tandem.

Every morning you pick up the same mug, but the coffee tastes either bitter or just right. It's not about the coffee, and not about your character. Inside us, an invisible panel with dozens of sliders is constantly shifting: fatigue, hunger, anxiety, hormone levels.

A person looks at a door lock and sees a keyhole. They know that a key is inserted and turned. But if instead of a keyhole there's a touch panel, the familiar frame breaks. The person doesn't just make a mistake: they realize that the usual approach won't work and can say, "There's no place for a key here; a different approach is needed." Such an honest stop with an explanation is rare for machines.

A tightrope walker inches across a chasm. As long as they keep their balance and avoid sudden moves, they're safe. But one overcorrection, and a fall is inevitable. Life works much the same way at every level — from proteins inside a cell to entire ecosystems.

When black holes collide, the very fabric of spacetime trembles. That rumble, gravitational waves, gets picked up by detectors, but decoding the signal used to take hours of computer simulation.

An orchestra plays without a conductor. Each musician has a score: that's the genes. But the volume and tempo depend on the acoustics of the hall, the mood, and the neighbors on stage. That's roughly how heredity and daily life together shape a teenager's behavior.

A laser beam is split into dozens of thin filaments, passes through frosted glass, and reconverges to a single point. This is the workbench where the program took a seat. It received no instructions — only a general goal: figure out how light changes when passing through a scattering medium, and find something new.

Searching for a new material is like looking for a needle in a haystack, but here the haystack is millions of possible atomic combinations. In the past, scientists spent years trying out options in the lab, relying on intuition and luck. Now, artificial intelligence is stepping in, learning to 'understand' the language of crystals.

A lab assistant carefully follows every step of an experiment, but at the end, writes in the report what they wanted to write before they even started. That's how modern language models behave when given scientific research tasks.

In a lab where crystals are studied, a technician stares at a screen covered in bright spots and slowly rotates the sample, trying to get the spots to form a symmetric pattern. It's like tuning an old radio: you turn the knob until the static gives way to a clear signal. Now, a machine can turn that knob. Scientists have created a program that learns to align crystals without any knowledge of how those spots work.

The best AI assistant for scientists scored worse on this exam than a C student on a pop quiz. Just 21% correct answers, and that's the ceiling for the four strongest models. The problems for the new test were written not by programmers but by graduate students: people who deal with real science every day. The test is called COMPOSITE-STEM.

An amoeba turns left. For a long time, this was considered the result of a rigid chain of causes, like dominoes. But at the core of matter, there's a gap for freedom. The 'Agent Choice via Quantum Flux' model shows: each decision corresponds not to one, but to many quantum histories.