{"paper":{"title":"From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models","arxiv_id":"2610.24676","primary_cat":"cs.CV","submitted_at":"2026-10-17T13:03:34+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.96,"id":"s0","own":false,"role":"background","text":"Vision-language models (VLMs) have achieved remarkable progress in 2D visual understanding tasks, yet the passive view-centric perception paradigm limits their capacity for 3D spatial reasoning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.15,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.0,"background":0.96,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.99,"id":"s1","own":false,"role":"background","text":"Such reasoning often requires actively acquiring spatial evidence beyond the currently visible views, such as camera poses and cross-view spatial relationships, to infer 3D relationships that are not explicitly represented in 2D images.","hedge":{"p":0.62,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":false,"role":"gap","text":"However, existing methods either lack active exploration or merely provide additional views during inference, without explicitly acquiring such spatial evidence beyond 2D images.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.18,"role_probabilities":{"gap":0.99,"method":0.0,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"contribution","text":"In this paper, we propose View-to-World (V2W), an active exploration framework that enables VLMs to actively explore 3D worlds and lifts VLMs from passive view-centric perception to active world-centric spatial reasoning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.2,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"method","text":"Given a spatial reasoning task with multi-view images, V2W first reconstructs an explicit 3D world with geometry, camera poses, and language-grounded semantics, and exposes it to VLMs through visual and linguistic interfaces.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.83,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"Through multi-turn interaction with these interfaces, VLMs iteratively acquire spatial evidence from the constructed 3D world, enabling active world-centric spatial reasoning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.58,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":6,"p":0.73,"id":"s6","own":true,"role":"method","text":"V2W can be integrated with existing VLMs in a training-free manner and can be further enhanced by optimizing the exploration policy via reinforcement learning.","hedge":{"p":0.71,"label":"asserted"},"own_p":0.6,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.73,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.27,"interpretation":0.0}},{"i":7,"p":0.98,"id":"s7","own":true,"role":"result","text":"Experiments on spatial mental modeling benchmarks demonstrate that V2W substantially improves VLM baselines in the training-free setting and achieves state-of-the-art performance with the learned exploration policy, highlighting the importance of active exploration for spatial intelligence.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.81,"quantitative":true,"quantitative_p":0.77,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":8,"p":0.55,"id":"s8","own":false,"role":"future_work","text":"Project page: \\url{https://fangzhou2000.github.io/projects/v2w}.","hedge":{"p":0.98,"label":"unclear"},"own_p":0.14,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.04,"background":0.15,"limitation":0.0,"future_work":0.55,"contribution":0.23,"interpretation":0.01}}]},"compiled":{"main_claim":{"p":0.99,"text":"Experiments on spatial mental modeling benchmarks demonstrate that V2W substantially improves VLM baselines in the training-free setting and achieves state-of-the-art performance with the learned exploration policy, highlighting the importance of active exploration for spatial intelligence.","location":"abstract s7","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7116,"cost_usd_reported":0.0},"compiled_at":"2026-10-20","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.14,"states_limitation":0.1,"human_participants":0.03,"controlled_comparison":0.84,"randomized_assignment":0.02,"states_quantitative_result":0.05,"compares_with_prior_results":0.93,"mentions_code_or_data_availability":0.35},"evidential_basis":{"p":0.99,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.99,"simulation_or_computation":0.01}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.99,"text":"In this paper, we propose View-to-World (V2W), an active exploration framework that enables VLMs to actively explore 3D worlds and lifts VLMs from passive view-centric perception to active world-centric spatial reasoning.","location":"abstract s3"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}