AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning

xiao chen, Dong Fang, HAITAO LI, Qing Li

NeurIPS 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes IntentLens, a tool-augmented reasoning approach for grounding underspecified multimodal queries (reference image plus fuzzy text) into recommendations.

Problem

Recommenders struggle when users give only a reference image and a fuzzy natural-language query, leaving visual attributes, personal preferences, and situational constraints implicit.

Approach

Uses tool-augmented reasoning to ground implicit intent from underspecified multimodal evidence before recommending; details not stated in the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add tool-augmented grounding (ground-then-rank) to MLLM recommender (ablation)IntentLens (7B) · Google Review-MMToolMRR: 33.5 -> 40.2 (w/o grounding)Improved
add visual tools (ablation)IntentLens (7B) · Google Review-MMToolMRR: 35.7 -> 40.2Improved
add user memory tools (ablation)IntentLens (7B) · Google Review-MMToolMRR: 38.1 -> 40.2Improved
add item attribute tools (ablation)IntentLens (7B) · Google Review-MMToolMRR: 38.0 -> 40.2Improved
add ranker-aligned reinforcement fine-tuning over SFT (ablation)IntentLens (7B) · Google Review-MMToolMRR: 33.1 -> 40.2Improved
add counterfactual no-tool baseline to reward (ablation)IntentLens (7B) · Google Review-MMToolMRR: 35.0 -> 40.2Improved
add item-side tool-selection reward (ablation)IntentLens (7B) · Google Review-MMToolMRR: 35.5 -> 40.2Improved
mask observation tokens in GRPO losses (ablation)IntentLens (7B) · Google Review-MMToolMRR: 35.1 -> 40.2Improved
scale backbone from 3B to 7BIntentLens · Google Review-MMTool and Yelp-MMToolMRR: 34.5 -> 40.2; 33.5 -> 46.7Improved
use predicted grounded query instead of raw query (ablation)IntentLens ranker · Google Review-MMToolMRR: 33.6 -> 40.2 (oracle-grounded 44.4)Improved
evaluate on unseen categories, cross-dataset, unseen toolsIntentLens (7B) · Google and YelpMRR: Google 40.2 -> 36.2 / 34.7 / 35.8Hurt
use IntentLens instead of GPT-5.4 with evidence on GoogleIntentLens (7B) · Google Review-MMToolHit@1 / MRR: Hit@1 31.0 vs 31.0; MRR 40.2 vs 41.6No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy