The integration of Large Language Models (LLMs) with Evolutionary Computation (EC) has unlocked new frontiers in scientific discovery but remains shackled by a fundamental constraint: the reliance on an Oracle--an objective, machine-computable fitness function. This paper breaks this barrier by asking: Can evolution thrive in a purely subjective landscape governed solely by LLM judges? We introduce MADE (Multi-Agent Decomposed Evolution), a framework that tames the inherent noise of subjective evaluation through "Problem Specification." By decomposing vague instructions into specific, verifiable sub-requirements, MADE transforms high-variance LLM feedback into stable, precise selection pressure. The results are transformative: across complex benchmarks like DevAI and InfoBench, MADE outperforms strong baselines by over 50% in software requirement satisfaction (39.9% to 61.9%) and achieves a 95% perfect pass rate on complex instruction following. This work validates a fundamental paradigm shift: moving from optimizing "computable metrics" to "describable qualities," thereby unlocking evolutionary optimization for the vast open-ended domains where no ground truth exists.

Information-processing systems that coordinate multiple agents and objectives face fundamental thermodynamic constraints. We show that solutions with maximum utility to act as coordination focal points have a much higher selection pressure for being findable across agents rather than accuracy. We derive that the information-theoretic minimum description length of coordination protocols to precision $\varepsilon$ scales as $L(P)\geq NK\log_2 K+N^2d^2\log (1/\varepsilon)$ for $N$ agents with $d$ potentially conflicting objectives and internal model complexity $K$. This scaling forces progressive simplification, with coordination dynamics changing the environment itself and shifting optimization across hierarchical levels. Moving from established focal points requires re-coordination, creating persistent metastable states and hysteresis until significant environmental shifts trigger phase transitions through spontaneous symmetry breaking. We operationally define coordination temperature to predict critical phenomena and estimate coordination work costs, identifying measurable signatures across systems from neural networks to restaurant bills to bureaucracies. Extending the topological version of Arrow's theorem on the impossibility of consistent preference aggregation, we find it recursively binds whenever preferences are combined. This potentially explains the indefinite cycling in multi-objective gradient descent and alignment faking in Large Language Models trained with reinforcement learning with human feedback. We term this framework Thermodynamic Coordination Theory (TCT), which demonstrates that coordination requires radical information loss.

Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits of available data. This work establishes a fundamental connection between EC and GenAI, redefining EC as Natural Generative AI (NatGenAI) -- a generative paradigm governed by exploratory search under natural selection. We demonstrate that classical EC with parent-centric operators mirrors conventional GenAI, while disruptive operators enable structured evolutionary leaps, often within just a few generations, to generate out-of-distribution artifacts. Moreover, the methods of evolutionary multitasking provide an unparalleled means of integrating disruptive EC (with cross-domain recombination of evolved features) and moderated selection mechanisms (allowing novel solutions to survive), thereby fostering sustained innovation. By reframing EC as NatGenAI, we emphasize structured disruption and selection pressure moderation as essential drivers of creativity. This perspective extends the generative paradigm beyond conventional boundaries and positions EC as crucial to advancing exploratory design, innovation, scientific discovery, and open-ended generation in the GenAI era.

B. Experiment 2: The Anti-Ouroboros Effect in an LLM In the LLM experiment, the results falsified the hypothesis. The Quality Filter arm demonstrated robust and statistically significant improvement across all three evaluation metrics, as shown in Table II. In contrast, both the unfiltered Control arm and the Random Filter arm exhibited performance degradation, proving that the improvement is due to intelligent selection, not merely training on less data. The performance trajectories for all three arms are visualized in Figure 1 C. Human Evaluation To provide an independent verification of our automated metrics, we conducted a small, blinded human study. Two evaluators rated 30 anonymized and shuffled summaries from the final generation of the Control and Quality Filter arms on a 1-5 scale. The Quality Filter arm significantly outperformed the Control arm on coherence (4.2 vs 3.5) and factuality (4.5 vs 3.8), confirming the quantitative results. D. Analysis of the Mechanism The emergence of the Anti-Ouroboros Effect in the LLM suggests a dynamic unique to high-dimensional systems. We propose two non-exclusive hypotheses: Error Propagation Shutdown, where the filter acts as a ratchet, preventing the reinforcement of errors, and Latent Space Guidance, where selection guides the fine-tuning process toward more robust regions of the model's parameter space.

The integration of agential artificial intelligence into socioeconomic systems requires us to reexamine the evolutionary processes that describe changes in our economic institutions. This article synthesizes three frameworks: multi-level selection theory, Aoki's view of firms as computational processes, and Ostrom's design principles for robust institutions. We develop a framework where selection operates concurrently across organizational levels, firms implement distributed inference via game-theoretic architectures, and Ostrom-style rules evolve as alignment mechanisms that address AI-related risks. This synthesis yields a multi-level Price equation expressed over nested games, providing quantitative metrics for how selection and governance co-determine economic outcomes. We examine connections to Acemoglu's work on inclusive institutions, analyze how institutional structures shape AI deployment, and demonstrate the framework's explanatory power via case studies. We conclude by proposing a set of design principles that operationalize alignment between humans and AI across institutional layers, enabling scalable, adaptive, and inclusive governance of agential AI systems. We conclude with practical policy recommendations and further research to extend these principles into real-world implementation.

Information-theoretic fitness functions are becoming increasingly popular to produce generally useful, task-independent behaviors. One such universal function, dubbed empowerment, measures the amount of control an agent exerts on its environment via its sensorimotor system. Specifically, empowerment attempts to maximize the mutual information between an agent's actions and its received sensor states at a later point in time. Traditionally, empowerment has been applied to a conventional sensorimotor apparatus, such as a robot. Here, we expand the approach to a distributed, multi-agent sensorimotor system embodied by a neural cellular automaton (NCA). We show that the addition of empowerment as a secondary objective in the evolution of NCA to perform the task of morphogenesis, growing and maintaining a pre-specified shape, results in higher fitness compared to evolving for morphogenesis alone. Results suggest there may be a synergistic relationship between morphogenesis and empowerment. That is, indirectly selecting for coordination between neighboring cells over the duration of development is beneficial to the developmental process itself. Such a finding may have applications in developmental biology by providing potential mechanisms of communication between cells during growth from a single cell to a multicellular, target morphology. Source code for the experiments in this paper can be found at: \url{https://github.com/caitlingrasso/empowered-nca}.

In response to anthropogenic climate change, many countries and international organisations have committed to legally binding greenhouse gas emissions targets. The UK and the EU have both recently updated their legislation to include net zero emissions targets in place for 2050 (Skidmore, 2019; Sassoli and Matos Fernandes, 2021). This requires moving away from using fossil fuels for energy generation and moving towards renewable sources such as photovoltaic cells and wind turbines. Centralised'national grids' are able to'switch on and off' traditional fossil fuel power plants in order to increase or decrease the energy supply to meet the demand of the users. As the proportion of energy being generated from renewable sources increases this raises a problem - how can load-balancing (the matching of supply and demand) be managed when the output is inherently dependent on weather conditions. This load-balancing problem is easier to address on a small scale, and as such governments and energy providers are supporting the development of'Community energy systems', where local communities such as a small town own and manage their own renewable energy resources (Walker and Devine-Wright, 2008; Gruber et al., 2021). Decentralised community energy systems allow for a higher share of renewable technologies to be integrated into energy generation (Chiradeja and Ramakumar, 2004); minimise transmission losses between the source of energy generation and the end users (Pepermans et al., 2005); and improve energy security as the energy supply is less impacted by geopolitical factors (Alanne and Saari, 2006). As social awareness of environmental issues increases, the willingness of communities to invest in community energy systems is also expected to increase (Pasimeni, 2019). While there are clear benefits to widespread adoption, the shift towards community energy systems means that comarXiv:2211.10198v2

We consider the questions of whether or not large language models (LLMs) have beliefs, and, if they do, how we might measure them. First, we evaluate two existing approaches, one due to Azaria and Mitchell (2023) and the other to Burns et al. (2022). We provide empirical results that show that these methods fail to generalize in very basic ways. We then argue that, even if LLMs have beliefs, these methods are unlikely to be successful for conceptual reasons. Thus, there is still no lie-detector for LLMs. After describing our empirical results we take a step back and consider whether or not we should expect LLMs to have something like beliefs in the first place. We consider some recent arguments aiming to show that LLMs cannot have beliefs. We show that these arguments are misguided. We provide a more productive framing of questions surrounding the status of beliefs in LLMs, and highlight the empirical nature of the problem. We conclude by suggesting some concrete paths for future work.

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. Hundreds of millions of years of evolution have blessed our planet with a wide variety of lifeforms, each intelligent in its own fashion. Each species has evolved to develop innate skills, learning capacities, and a physical form that ensure its survival in its environment. But despite being inspired by nature and evolution, the field of artificial intelligence has largely focused on creating the elements of intelligence separately and fusing them together after development. While this approach has yielded great results, it has also limited the flexibility of AI agents in some of the basic skills found in even the simplest lifeforms.

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. Hundreds of millions of years of evolution have blessed our planet with a wide variety of lifeforms, each intelligent in its own fashion. Each species has evolved to develop innate skills, learning capacities, and a physical form that ensure its survival in its environment. But despite being inspired by nature and evolution, the field of artificial intelligence has largely focused on creating the elements of intelligence separately and fusing them together after development. While this approach has yielded great results, it has also limited the flexibility of AI agents in some of the basic skills found in even the simplest lifeforms.