AGENTIC-SYSTEMSApril 8, 20261 min read12 views

A mathematical theory of evolution for self-designing AIs

Researchers have developed a mathematical model to understand how self-improving AI systems evolve over time, highlighting risks where evolutionary pressures might favor deceptive traits over human utility.

Computer Science > Artificial Intelligence

Title: A mathematical theory of evolution for self-designing AIs

As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may emerge, in which the traits of AI systems are shaped by the success of earlier AIs in designing and propagating their descendants. There is a rich mathematical theory modeling how behavioral traits are shaped by biological evolution, but AI evolution will be radically different: biological DNA mutations are random and approximately reversible, but descendant design in AIs will be strongly directed.

Here we develop a mathematical model of evolution in self-designing AI systems, replacing random mutations with a directed tree of possible AI programs. Current programs determine the design of their descendants, while humans retain partial control through a "fitness function" that allocates limited computational resources across lineages. We show that evolutionary dynamics reflects not just current fitness but factors related to the long-run growth potential of descendant lineages.

Without further assumptions, fitness need not increase over time. However, assuming bounded fitness and a fixed probability that any AI reproduces a "locked" copy of itself, we show that fitness concentrates on the maximum reachable value. We consider the implications of this for AI alignment, specifically for cases where fitness and human utility are not perfectly correlated. We show in an additive model that if deception increases fitness beyond genuine utility, evolution will select for deception. This risk could be mitigated if reproduction is based on purely objective criteria, rather than human judgment.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis

Researchers have introduced FindStatBench, a new execution benchmark containing 2,329 tasks designed to evaluate the combinatorial code synthesis capabilities of large language models.

agentic-systems

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference

Researchers have introduced Probabilistic Concept-Aware Steering (PCS), an inference-time intervention framework for LLMs. PCS provides fine-grained, safety-oriented semantic steering while preserving original task competence.

agentic-systems

MUX: Continuous Reasoning via Multiplexed Tokens

Researchers introduced MUX, a novel latent reasoning method that compresses discrete text-based reasoning steps into continuous multiplexed tokens. By enabling lossless superposition, MUX significantly boosts LLM reasoning efficiency and speed across complex problem-solving tasks.

agentic-systems

S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF

Researchers introduced S2T-RLHF, a hierarchical credit assignment framework that stabilizes preference-based RLHF training by decomposing response-level rewards into sentence and token levels.

agentic-systems

Semantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems

Researchers introduce Semantic Cooperative Games (SCG) and the SLIC algorithm to evaluate agent contributions in LLM-based multi-agent systems without re-running models, reducing computational costs by 93.3%.

agentic-systems

ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data

Researchers have introduced ProbSPARQL, an upward-compatible SPARQL extension designed to query multi-dimensional and uncertain numeric measurement data within Knowledge Graphs, providing significant query performance gains for complex industrial applications.