This work introduces MMShopBench, the first real-log benchmark for multimodal, multi-turn shopping agents, and builds an offline shopping sandbox, where fine-tuning substantially narrows the performance gap between the open-source model and leading proprietary models.
Abstract
Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult to articulate in text alone. However, existing benchmarks largely rely on text-only or synthetic requests, underrepresenting complex real-world shopping requirements jointly expressed through images and language. We introduce MMShopBench, the first real-log benchmark for multimodal, multi-turn shopping agents. Built from carefully cleaned and manually annotated shopping logs, MMShopBench provides ground-truth annotations of each request's purchase intent and mandatory product requirements. Agents must infer these requirements jointly from user images and multi-turn dialogue, retrieve candidate products through image and text search, and verify that each candidate satisfies all requirements using its product images and structured attributes. We evaluate representative open-source and proprietary models using an evidence-grounded multimodal protocol and construct a companion training set for fine-tuning an open-source model. To ensure reproducible experimentation, we build an offline shopping sandbox, where fine-tuning substantially narrows the performance gap between our open-source model and leading proprietary models, demonstrating the effectiveness of our training data.
A unified taxonomy of 8 categories covering ambiguous and unanswerable questions is addressed, a multi-agent generation pipeline with a two-stage process (NLQ generation followed by SQL grounding) and an explicit Category Conformance validation stage are addressed.
Giovanni Sullutrone, Luca Sala, Sania Aftar et al.· arXiv.org· 0 citations
Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a stricter requirement: recommendations must be drawn only from a merchant's fixed catalog, without web search or unsupported product claims. In this setting, the main challenge is reliability under hard constraints: the system must satisfy user requirements, remain grounded in available inventory, and preserve preferences across multiple conversational turns. We present MACS (Multi-Agent Commerce System), a hybrid multi-agent framework for reliable conversational recommendation in fixed-catalog settings. MACS uses LLMs for language-facing tasks such as interpreting user requests, eliciting preferences, and generating responses, while correctness-critical operations, including product retrieval, hard-constraint filtering, brand exclusion, and progressive relaxation, are executed deterministically by the merchant agent. A session-persistent preference layer tracks constraints across turns, enabling consistent handling of budget overwrites and exclusion reversals. On a 140-query single-turn benchmark, MACS achieves the highest pass rate (87.1%) and perfect brand compliance (1.000). On a 10-scenario multi-turn benchmark, MACS achieves the strongest macro Pass@5 (72% vs. 56% GPT+Catalog / 52% Gemini+Catalog) with zero constraint drift. The advantage is sharpest on exclusion reversal (100% vs. 20% / 0%) and constraint accumulation (100% vs. 60% / 40%). Mean judged response quality is similar across systems (0.751 vs. 0.736). These results suggest that hybrid architectures combining deterministic constraint enforcement with session-persistent preference tracking provide stronger reliability-oriented performance than catalog-bound prompt-only baselines in the fixed-catalog merchant setting.
Ju-Li Huang, Hanna Clay, Sajjad Beygi et al.· 0 citations
The proposed Multi-turn Multimodal Interactive Dialogue (MMID) Benchmark enables comprehensive evaluation of the Perception, Memorization, and Reasoning abilities of MLLMs, and reveals MLLMs perform well with text-based input but degrade with images, requiring improved leverage fine-grained visual cues.
Seulgi Kim, Juoh Sun, Sumin Kim et al.· Proceedings of the 32nd ACM...· 0 citations
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a terminal reward, assigning the same credit to effective elicitation, errors, and later repair. The next user turn is more than context: it also provides noisy, temporally local evidence about the preceding user-to-user segment. We introduce \textbf{F}eedback-\textbf{A}ware \textbf{C}redit \textbf{A}ssignment (\textsc{FACA}), which aligns each reaction with that segment, derives a locally normalized reaction advantage, and adds it to verified terminal outcome advantage without an extra critic or rollout. Against an outcome-only Interactive GRPO control matched in simulator, visible dialogue, initialization, rollout, and optimization, \textsc{FACA} improves the nine-domain $\tau$-family average across three independently trained runs by 5.91 and 10.22 percentage points at 8B and 14B, respectively. Gains concentrate in Telecom; at 8B, randomizing reaction polarity removes the Telecom gain. The same ordering holds zero-shot on Pare-Bench and Co-Gym. These results demonstrate that next-turn user reactions provide actionable local credit for improving multi-turn user-interacting agents.
Yiwen Zhao, Zhihao Wen, Yuchen Mao et al.· 0 citations
Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware RL.The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks -- an improvement of 10.5 points over its base model Qwen3.5-35B-A3B -- and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).
