ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

TL;DR

ProactiveBench is a new benchmark for evaluating proactiveness in multimodal large language models, revealing current models' lack of proactive behavior and demonstrating that proactiveness can be learned through reinforcement learning.

Contribution

We introduce ProactiveBench, a comprehensive benchmark for proactiveness in MLLMs, and show that proactiveness can be learned via reinforcement learning, improving model behavior in various tasks.

Findings

Most MLLMs lack proactiveness.

Proactiveness does not correlate with model size.

Reinforcement learning enhances proactiveness.

Abstract

Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains. Surprisingly, we found that conversation histories and in-context learning introduce negative biases, hindering performance. Finally, we explore a simple fine-tuning strategy based on reinforcement learning: its results suggest that proactiveness can be learned, even generalizing to unseen scenarios. We publicly release ProactiveBench as a first step toward building proactive multimodal models.