Obtaining high-quality outputs from Large Language Models (LLMs) often depends upon the choice of a sampling-based decoding strategy to probabilistically choose the next token at each generation step. While a variety of such sampling methods have been proposed, their performance can be sensitive to the selection of hyperparameters which may require different settings depending upon the generation task and temperature configuration. In this work, we introduce $p$-less sampling: an information-theoretic approach to sampling which dynamically sets a truncation threshold at each decoding step based on the entire token probability distribution. Unlike existing methods, $p$-less sampling has no hyperparameters and consistently produces high-quality outputs as temperature increases. We provide theoretical perspectives on $p$-less sampling to ground our proposed method and conduct experiments to empirically validate its effectiveness across a range of math, logical reasoning, and creative writing tasks. Our results demonstrate how $p$-less sampling consistently outperforms existing sampling approaches while exhibiting much less degradation in text quality at higher temperature values. We further show how $p$-less achieves greater inference-time efficiency than alternative methods through lower average token sampling times and shorter generation lengths, without sacrificing accuracy. Finally, we provide analyses to highlight the benefits of $p$-less through qualitative examples, case studies, and diversity assessments. The code is available at https://github.com/ryttry/p-less .

Large Language Models (LLMs) are rapidly being adopted in conservation to address the biodiversity crisis, yet their reliability for species evaluation is uncertain. This study systematically validates five leading models on 21,955 species across four core IUCN Red List assessment components: taxonomy, conservation status, distribution, and threats. A critical paradox was revealed: models excelled at taxonomic classification (94.9%) but consistently failed at conservation reasoning (27.2% for status assessment). This knowledge-reasoning gap, evident across all models, suggests inherent architectural constraints, not just data limitations. Furthermore, models exhibited systematic biases favoring charismatic vertebrates, potentially amplifying existing conservation inequities. These findings delineate clear boundaries for responsible LLM deployment: they are powerful tools for information retrieval but require human oversight for judgment-based decisions. A hybrid approach is recommended, where LLMs augment expert capacity while human experts retain sole authority over risk assessment and policy.

Breakthroughs, discoveries, and DIY tips sent every weekday. Using advanced imaging techniques, an international research team has reconstructed an ancient extinct fish's heart, brain, and fins from an intricately detailed, fingernail-sized fossil fragment. But cartoon lookalikes aside, the creature may help rewrite one of the earliest chapters in animal evolution. Its details are described in a study published on August 6 in Nature. Earth's first fish arrived about half a billion years ago, but not anywhere near the ocean's surface.

Breakthroughs, discoveries, and DIY tips sent every weekday. Few predators swallow their prey whole. Even fewer can digest their meals with bones and all. Herpetologists have spent years trying to understand how bones are not only safe and healthy for the serpents, but how their biology manages to regulate when and how many bones to digest. Now, researchers believe they have identified an explanation hidden inside the "crypts" of specialized cells.

There are many remarkable things about octopuses--they're famously intelligent, they have three hearts, their eyeballs work like prisms, they can change color at will, and they can "see" light with their skin. One of the most striking things about these creatures, however, is the fact that each of their eight arms almost seems to have a mind of its own, allowing an octopus to multitask in a manner that humans can only dream about. At the heart of each arm is a structure known as the axial nervous cord (ANC), and a new study published January 15 in Nature Communications examines how the structure of this cord is fundamental to allowing the arms to act as they do. Cassady Olson, first author on the paper, explains to Popular Science that understanding the ANC is crucial to understanding how an octopus's arms work: "You can think of the ANC as equivalent to a spinal cord running down the center of every single arm." Olson explains that "there are many gross similarities [between the ANC and vertebrates' spinal cords]--there is a cell body region, a neuropil region, and long tracts to connect the arms and brains in each."

Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation. This work investigates the neural sub-structures within LLMs that manifest CoT reasoning from a mechanistic point of view. From an analysis of Llama-2 7B applied to multistep reasoning over fictional ontologies, we demonstrate that LLMs deploy multiple parallel pathways of answer generation for step-by-step reasoning. These parallel pathways provide sequential answers from the input question context as well as the generated CoT. We observe a functional rift in the middle layers of the LLM. Token representations in the initial half remain strongly biased towards the pretraining prior, with the in-context prior taking over in the later half. This internal phase shift manifests in different functional components: attention heads that write the answer token appear in the later half, attention heads that move information along ontological relationships appear in the initial half, and so on. To the best of our knowledge, this is the first attempt towards mechanistic investigation of CoT reasoning in LLMs.

Researchers at Kyoto University and Nagoya University in Japan have recently devised a new, automatic approach for designing robots that could simultaneously improve their shape, structure, movements, and controller components. This approach, presented in a paper published in Artificial Life and Robotics, draws inspiration from the evolution of vertebrates, the broad category of animals that possess a backbone or spinal column, which includes mammals, reptiles, birds, amphibians, and fishes. "The automatic robot design is a completely novel research project for the Matsuno Lab, the laboratory led by Fumitoshi Matsuno, and this is the first paper published for this project," Ryosuke Koike, one of the researchers who carried out the study, told TechXplore. "Its primary objective was to design a good-performing robot for a given task. Since there are innumerable possible combinations of robot morphologies and controllers, it is impossible to reach the best robot by manual human exploration. Therefore, we realized that it is necessary to establish a method for automatically designing robots using computers."

Intelligence in this "clean room" environment can be defined with respect to accumulated systematic methods of reasoning. So a logic proof system can be defined to be more efficient at solving a mathematical task than a comparable human. The more civilization transitions into a virtualized world, the more likely humans will find synthetic minds that are'more intelligent'. Classical definitions of computation tend to favor sequential processes. A consequence is that more natural parallel processes such as evolution tend to be ignored. Therefore a properly informed definition of intelligence must take into account how to scale parallel cognition.

Using the fossil and fossilized footprints of a 300-million-year-old animal, scientists from EPFL and Humboldt-Universität zu Berlin have identified the most likely gaits of extinct animals and designed a robot that can recreate an extinct animal's walk. This study can help researchers better understand how vertebrate locomotion evolved over time. How did vertebrates walk 300 million years ago? Could they already stand upright on their legs? Did they move in a balanced, energy-efficient way?

Tooth-like scales of sharks and chicken feathers are created by the same process and explained by a theory from the legendary code-breaker Alan Turing. His reaction-diffusion theory is widely accepted as the way in which many animals get unique patterns in their feathers, fur, teeth and teeth. It has now been extended to include the development of shark scales - a group of animals that are very distantly related to the other known animals. The findings help explain how the scales of a shark evolved to reduce drag and be more energy efficient while swimming. Scientists believe this patterning could help in designing shark-inspired materials to improve energy efficiency.