Salvato in:
Dettagli Bibliografici
Autori principali: Pasternak, Gil, Rajagopal, Dheeraj, White, Julia, Atreja, Dhruv, Thomas, Matthew, Hurn-Maloney, George, Lewis, Ash
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.19771
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908840231960576
author Pasternak, Gil
Rajagopal, Dheeraj
White, Julia
Atreja, Dhruv
Thomas, Matthew
Hurn-Maloney, George
Lewis, Ash
author_facet Pasternak, Gil
Rajagopal, Dheeraj
White, Julia
Atreja, Dhruv
Thomas, Matthew
Hurn-Maloney, George
Lewis, Ash
contents LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously. However, evaluating proactivity is challenging; current benchmarks are constrained to localized context, limiting their ability to test reasoning across sources and longer time horizons. To address this gap, we present PROBE (Proactive Resolution Of BottlEnecks). PROBE decomposes proactivity as a pipeline of three core capabilities: (1) searching for unspecified issues, (2) identifying specific bottlenecks, and (3) executing appropriate resolutions. We apply PROBE to evaluate leading LLMs and popular agentic frameworks, showing that even state-of-the-art models struggle to solve this benchmark. Computing our consistent measurements across frontier LLMs and agents, we find that the best end-to-end performance of 40% is achieved by both GPT-5 and Claude Opus-4.1. Additionally, we demonstrate the relative capabilities of each model and analyze mutual failure modes. Our results highlight the current limitations of autonomous action in agentic systems, and expose promising future research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
Pasternak, Gil
Rajagopal, Dheeraj
White, Julia
Atreja, Dhruv
Thomas, Matthew
Hurn-Maloney, George
Lewis, Ash
Artificial Intelligence
LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously. However, evaluating proactivity is challenging; current benchmarks are constrained to localized context, limiting their ability to test reasoning across sources and longer time horizons. To address this gap, we present PROBE (Proactive Resolution Of BottlEnecks). PROBE decomposes proactivity as a pipeline of three core capabilities: (1) searching for unspecified issues, (2) identifying specific bottlenecks, and (3) executing appropriate resolutions. We apply PROBE to evaluate leading LLMs and popular agentic frameworks, showing that even state-of-the-art models struggle to solve this benchmark. Computing our consistent measurements across frontier LLMs and agents, we find that the best end-to-end performance of 40% is achieved by both GPT-5 and Claude Opus-4.1. Additionally, we demonstrate the relative capabilities of each model and analyze mutual failure modes. Our results highlight the current limitations of autonomous action in agentic systems, and expose promising future research directions.
title Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2510.19771