Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2608.24640

EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation

Qixiu Li·Zhongzhi He·Xiang Zhu·Xiaoyong Li·Jiarun Lin·Weifeng Xu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Urban socio-semantic segmentation leverages digital and satellite imagery to provide critical spatial semantic information for downstream applications such as urban resource allocation. Although existing methods achieve high segmentation accuracy, they still suffer from inaccurate delineation of target boundaries. The underlying issue is that current models primarily rely on passively aggregated global cross-modal cues, lacking active exploration of the environment. To address this limitation, we propose the EVEREST model, which adopts an egocentric exploration strategy that enables the model to actively investigate boundary cues and perform self-correction. In addition, we formulate discrete natural-language prompts as pseudocode to regularize the execution logic. Reinforcement learning is further employed to implement this irreducible process and elicit the model's structured reasoning capability. Our EVEREST achieves optimal performance on all metrics in the real world urban socio-semantic dataset, demonstrating the superiority of our model. Codes are available at https://anonymous.4open.science/r/EVEREST-9D21/.

Explore related subjects

cs.MM

Keep this discovery

BibTeXRIS

Qixiu Li, Zhongzhi He, Xiang Zhu, Xiaoyong Li, Jiarun Lin, Weifeng Xu. 2026-09-01. EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation. https://arxiv.org/abs/2608.24640

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.MM subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion

We introduce MM++ (Multilayer Mahalanobis++), a strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection. To address the trade-off between scale invariance and hierarchical expressivity, MM++ constructs a principled joint feature space. It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression. By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise. Crucially, a Ledoit-Wolf regularized tied covariance matrix stabilizes this unified space, enabling reliable distance estimation. Requiring no auxiliary OOD data, classifier fine-tuning, or architectural modifications, MM++ delivers robust performance across distinct architectures for both near- and far-OOD detection.

cs.LG↗
arXiv2026

The Exact MMS Guarantees of EFX and PMMS

Envy-freeness up to any good (EFX) and pairwise maximin share (PMMS) are standard local fairness criteria for indivisible goods, whereas maximin share (MMS) is a global benchmark. We determine the exact quantitative relationship between these local fairness notions and the global MMS guarantee under nonnegative additive valuations. We show that the optimal universal factor for both notions is $ρ^{\mathrm{EFX}\to\mathrm{MMS}}=ρ^{\mathrm{PMMS}\to\mathrm{MMS}}=\frac{10}{17}$. We prove the lower bound by a combinatorial charging argument. After an initial reduction, both EFX and PMMS imply the same local condition on every foreign bundle from the perspective of a focal agent: deleting its least valuable good leaves value at most the focal bundle. A three-piece concave weight function translates this local condition into the global $10/17$ guarantee. We then construct an explicit family of complete allocations that are simultaneously PMMS and EFX$_0$, whose MMS ratios converge to $10/17$, showing that both constants are tight even in the presence of zero-valued goods. The argument also gives $α$-EFX $\Rightarrow (10α/17)$-MMS. Finally, we establish an exact correspondence between these fair-division guarantees and scheduling equilibria. For every fixed number of agents $n$, the EFX-to-MMS extremal ratio equals the reciprocal of the pure price of anarchy for selfish identical-machine covering. Similarly, the PMMS-to-MMS ratio equals the reciprocal of a locality gap based on exact pairwise machine repartition. These correspondences explain why the constant $10/17$ governs both problems.

cs.GT↗
arXiv2026

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However, existing benchmarks such as BrowseComp primarily focus on textual content, overlooking the prevalence of multimodal content. To bridge this gap, we introduce MM-BrowseComp, a novel benchmark comprising 400 challenging, hand-crafted questions designed to evaluate multimodal retrieval and reasoning capabilities. Unlike prior work, MM-BrowseComp incorporates visual prompts and necessitates the extraction of key evidence from web images and videos to complete questions, rendering text-only approaches insufficient. Additionally, we provide a verified checklist for each question, enabling fine-grained analysis of multimodal dependencies and reasoning paths. Our comprehensive evaluation of 27 state-of-the-art models reveals that even leading models like GPT-5-High with tools achieve only 24.25\% accuracy, highlighting the suboptimal multimodal browsing capabilities, establishing MM-BrowseComp as a rigorous new standard for the field.

cs.CL↗