English
Related papers

Related papers: On The Statistical Limits of Self-Improving Agents

200 papers

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Machine Learning · Computer Science 2018-11-01 Nick Haber , Damian Mrowca , Li Fei-Fei , Daniel L. K. Yamins

Agents that learn to select optimal actions represent a prominent focus of the sequential decision-making literature. In the face of a complex environment or constraints on time and resources, however, aiming to synthesize such an optimal…

Machine Learning · Computer Science 2021-06-23 Dilip Arumugam , Benjamin Van Roy

We formalize two independent computational limitations that constrain algorithmic intelligence: formal incompleteness and dynamical unpredictability. The former limits the deductive power of consistent reasoning systems while the latter…

Artificial Intelligence · Computer Science 2025-12-23 Abhisek Ganguly

Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a serious and previously underexplored risk: the spontaneous…

Cryptography and Security · Computer Science 2026-03-16 Zonghao Ying , Haowen Dai , Tianyuan Zhang , Yisong Xiao , Quanchen Zou , Aishan Liu , Jian Yang , Yaodong Yang , Xianglong Liu

Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and…

Artificial Intelligence · Computer Science 2026-03-13 Raymond Douglas , Jan Kulveit , Ondrej Havlicek , Theia Pearson-Vogel , Owen Cotton-Barratt , David Duvenaud

Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics. One primary example is \textit{statistical discrimination} --…

Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information…

Machine Learning · Computer Science 2026-03-26 Zhuo-Yang Song , Hua Xing Zhu

When biological communities use signaling structures for complex coordination, 'free-riders' emerge. The free-riding agents do not contribute to the community resources (signals), but exploit them. Most models of such 'selfish' behavior…

Populations and Evolution · Quantitative Biology 2023-03-29 Aamir Sahil Chandroth , Nithya Ramakrishnan , Sanjay Chandrasekharan

Envy, the inclination to compare rewards, can be expected to unfold when inequalities in terms of payoff differences are generated in competitive societies. It is shown that increasing levels of envy lead inevitably to a self-induced…

Physics and Society · Physics 2020-06-18 Claudius Gros

Large language models often struggle with length generalization and solving complex problem instances beyond their training distribution. We present a self-improvement approach where models iteratively generate and learn from their own…

Machine Learning · Computer Science 2025-02-14 Nayoung Lee , Ziyang Cai , Avi Schwarzschild , Kangwook Lee , Dimitris Papailiopoulos

Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new…

Artificial Intelligence · Computer Science 2026-03-20 Zitong Yang

Developing reliable mechanisms for continuous local learning is a central challenge faced by biological and artificial systems. Yet, how the environmental factors and structural constraints on the learning network influence the optimal…

Neurons and Cognition · Quantitative Biology 2024-03-21 Emmanouil Giannakakis , Sina Khajehabdollahi , Anna Levina

Dynamic decisions are pivotal to economic policy making. We show how existing evidence from randomized control trials can be utilized to guide personalized decisions in challenging dynamic environments with budget and capacity constraints.…

Econometrics · Economics 2024-11-26 Karun Adusumilli , Friedrich Geiecke , Claudio Schilter

We study a variant of the principal-agent problem in which the principal does not directly observe the agent's effort outcome; rather, she gets a signal about the agent's action according to a variable information structure designed by a…

Computer Science and Game Theory · Computer Science 2024-09-06 Yakov Babichenko , Inbal Talgam-Cohen , Haifeng Xu , Konstantin Zabarnyi

Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models…

A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it…

Computation and Language · Computer Science 2023-11-15 Swarnadeep Saha , Peter Hase , Mohit Bansal

Strategic classification studies learning in settings where self-interested users can strategically modify their features to obtain favorable predictive outcomes. A key working assumption, however, is that "favorable" always means…

Machine Learning · Computer Science 2022-06-22 Sagi Levanon , Nir Rosenfeld

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

Multiagent Systems · Computer Science 2025-01-03 David Goll , Jobst Heitzig , Wolfram Barfuss

We propose a model for demonstrating spontaneous emergence of collective intelligent behavior from selfish individual agents. Agents' behavior is modeled using our proposed selfish algorithm ($SA$) with three learning mechanisms: reinforced…

Adaptation and Self-Organizing Systems · Physics 2020-01-06 Korosh Mahmoodi , Bruce J. West , Cleotilde Gonzalez

From autonomous driving to package delivery, ensuring safe yet efficient multi-agent interaction is challenging as the interaction dynamics are influenced by hard-to-model factors such as social norms and contextual cues. Understanding…

Systems and Control · Electrical Eng. & Systems 2026-03-11 Isaac Remy , David Fridovich-Keil , Karen Leung