{"paper":{"title":"In-Context Robot Learning with VLM Agents","arxiv_id":"2609.19138","primary_cat":"cs.CV","submitted_at":"2026-09-16T17:58:35+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":1.0,"id":"s0","own":false,"role":"background","text":"Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.96,"id":"s1","own":false,"role":"background","text":"No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.41,"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":2,"p":0.99,"id":"s2","own":false,"role":"gap","text":"Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies.","hedge":{"p":0.99,"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":0.56,"id":"s3","own":false,"role":"background","text":"The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters?","hedge":{"p":0.49,"label":"hedged_possibility"},"own_p":0.05,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.42,"method":0.0,"result":0.0,"background":0.56,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"contribution","text":"We introduce GPT-Policy, a general-agent framework for in-context robot learning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.98,"interpretation":0.0}},{"i":5,"p":0.96,"id":"s5","own":true,"role":"method","text":"GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.77,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.96,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":6,"p":0.94,"id":"s6","own":true,"role":"method","text":"We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.95,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.16,"role_probabilities":{"gap":0.0,"method":0.94,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.17,"quantitative":true,"quantitative_p":0.72,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"interpretation","text":"These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment.","hedge":{"p":0.5,"label":"asserted"},"own_p":0.78,"main_claim_p":0.87,"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":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":0.99,"text":"These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment.","location":"abstract s8","hedge_strength":{"p":0.5,"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":6981,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.86,"human_participants":0.4,"controlled_comparison":0.74,"randomized_assignment":0.02,"states_quantitative_result":0.06,"compares_with_prior_results":0.8,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"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":0.96,"text":"We introduce GPT-Policy, a general-agent framework for in-context robot learning.","location":"abstract s4"}},"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"}}}