ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models episode artwork

EPISODE · Mar 24, 2026 · 20 MIN

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 30 | cs.CV Authors: Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini Title: ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models Arxiv: http://arxiv.org/abs/2603.19466v1 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.

Episode metadata supplied by the publisher feed · Published Mar 24, 2026

🤗 Upvotes: 30 | cs.CV Authors: Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini Title: ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models Arxiv: http://arxiv.org/abs/2603.19466v1 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.

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

0:00 20:44

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 20 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on March 24, 2026.

What is this episode about?

🤗 Upvotes: 30 | cs.CV Authors: Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini Title: ProactiveBench: Benchmarking Proactiveness in Multimodal...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!