paper-with-me

홈 › Papers

RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents

2025-04-21 · Sid Black, Asa Cooper Stickland, Jake Pencharz, Oliver Sourbut, Michael Schmatz, Jay Bailey, Ollie Matthews, Ben Millwood, Alex Remedios, Alan Cooney

Uncontrollable autonomous replication of language model agents poses a critical safety risk. To better understand this risk, we introduce RepliBench, a suite of evaluations designed to measure autonomous replication capabilities. RepliBench is derived from a decomposition of these capabilities covering four core domains: obtaining resources, exfiltrating model weights, replicating onto compute, and persisting on this compute for long periods. We create 20 novel task families consisting of 86 individual tasks. We benchmark 5 frontier models, and find they do not currently pose a credible threat of self-replication, but succeed on many components and are improving rapidly. Models can deploy instances from cloud compute providers, write self-propagating programs, and exfiltrate model weights under simple security setups, but struggle to pass KYC checks or set up robust and persistent agent deployments. Overall the best model we evaluated (Claude 3.7 Sonnet) has a >50% pass@10 score on 15/20 task families, and a >50% pass@10 score for 9/20 families on the hardest variants. These findings suggest autonomous replication capability could soon emerge with improvements in these remaining areas or with human assistance.

📄 PDF Abstract BibTeX arXiv:2504.18565

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

SOCK: A Benchmark for Measuring Self-Replication in Large Language Models

2025-09-30 · Justin Chavarria, Rohan Raizada, Justin White, Eyad Alhetairshi arxiv

We introduce SOCK, a benchmark command line interface (CLI) that measures large language models' (LLMs) ability to self-replicate without human intervention. In this benchmark, self-replication is defined not only as an …

Evaluating Language-Model Agents on Realistic Autonomous Tasks

2023-12-18 · Megan Kinniment, Lucas Jun Koba Sato, Haoxing Du, Brian Goodrich 외

In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "au…

Language ModelingLanguage Modellingmodel

Automatic Classification of User Requirements from Online Feedback -- A Replication Study

2025-07-29 · Meet Bhatt, Nic Boilard, Muhammad Rehan Chaudhary, Cole Thompson 외 arxiv

Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field to support tasks such as classification and ambiguity detection. Although RE research is rooted in empirica…

From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking

2025-06-24 · Gyeongwon James Kim, Alex Wilf, Louis-Philippe Morency, Daniel Fried

Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether su…

Code Generationscientific discovery

Co-evolution of self-replication and function in a digital primordial soup

2026-07-10 · Francesco Cicala, Eyvind Niklasson, Ettore Randazzo, Sami Boukortt 외 arxiv

While traditional evolutionary algorithms hard-code reproduction, self-replication can emerge spontaneously within digital ``primordial soups''. This paper investigates the co-evolution of this emergent self-replication …