{"paper":{"title":"EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence","arxiv_id":"2610.18867","primary_cat":"cs.RO","submitted_at":"2026-10-13T17:59:51+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":"Bringing general-purpose agents into the physical world calls for an executable representation of physical intelligence.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.02,"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":0.99,"id":"s1","own":false,"role":"background","text":"Compared with vision-language-action (VLA) models, which map observations and language instructions directly to actions, code makes control logic explicit and reusable.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.44,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.81,"id":"s2","own":false,"role":"background","text":"Code can serve not only as a policy representation but also as the workspace in which the agent solves a task.","hedge":{"p":0.53,"label":"asserted"},"own_p":0.1,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.12,"result":0.0,"background":0.81,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.01}},{"i":3,"p":0.92,"id":"s3","own":false,"role":"method","text":"Rather than following a prescribed workflow of planning, execution, and verification, the agent can autonomously inspect the state, revise and execute code, and use feedback to choose the next step.","hedge":{"p":0.51,"label":"asserted"},"own_p":0.29,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.92,"result":0.0,"background":0.03,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.0}},{"i":4,"p":0.92,"id":"s4","own":false,"role":"background","text":"The success of this SWE-style loop in digital environments motivates its extension to physical tasks.","hedge":{"p":0.84,"label":"asserted"},"own_p":0.09,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.03,"method":0.0,"result":0.0,"background":0.92,"limitation":0.0,"future_work":0.01,"contribution":0.0,"interpretation":0.04}},{"i":5,"p":0.54,"id":"s5","own":false,"role":"gap","text":"Yet physical execution remains prone to recurring failures.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.16,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.54,"method":0.0,"result":0.0,"background":0.4,"limitation":0.05,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.71,"id":"s6","own":true,"role":"contribution","text":"To retain and refine experience for later scenes, we introduce EmbodiedEvo, where a coding agent evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for diverse new scenes.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.2,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.29,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.71,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82\\%, surpassing all officially verified results.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.3,"quantitative":true,"quantitative_p":0.99,"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":0.93,"id":"s8","own":true,"role":"result","text":"Paired tests show the largest gains on memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remains difficult.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.16,"quantitative":true,"quantitative_p":0.66,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.93,"background":0.0,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.05}},{"i":9,"p":0.99,"id":"s9","own":true,"role":"result","text":"Experience from stronger models also improves weaker executors: Astra's experience raises Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":10,"p":1.0,"id":"s10","own":true,"role":"result","text":"Compared with raw interaction history, Skills and Lessons achieve comparable task performance at 53.0\\% lower execution cost.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.15,"quantitative":true,"quantitative_p":0.99,"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}}]},"compiled":{"main_claim":{"p":0.74,"text":"On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82\\%, surpassing all officially verified results.","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":8191,"cost_usd_reported":0.0},"compiled_at":"2026-10-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.96,"human_participants":0.03,"controlled_comparison":0.95,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.97,"mentions_code_or_data_availability":0.05},"evidential_basis":{"p":0.53,"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":0.53,"simulation_or_computation":0.47}},"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":1.0,"text":"To retain and refine experience for later scenes, we introduce EmbodiedEvo, where a coding agent evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for diverse new scenes.","location":"abstract s6"}},"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":11,"sentences_in_abstract":11},"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"}}}