{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWL7XSKMMPVFWIMWM2JGWFUPSV","short_pith_number":"pith:QWL7XSKM","schema_version":"1.0","canonical_sha256":"8597fbc94c63ea5b219666926b168f9557ec028e0c86b65af7d6be11294c071a","source":{"kind":"arxiv","id":"2407.13505","version":2},"attestation_state":"computed","paper":{"title":"Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Burak Can Kaplan, Carlo Mazzola, Giulia Belgiovine, Hassan Ali, Luk\\'a\\v{s} Gajdo\\v{s}ech, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-07-18T13:38:21Z","abstract_excerpt":"Large Language Models (LLMs) have been recently used in robot applications for grounding LLM common-sense reasoning with the robot's perception and physical abilities. In humanoid robots, memory also plays a critical role in fostering real-world embodiment and facilitating long-term interactive capabilities, especially in multi-task setups where the robot must remember previous task states, environment states, and executed actions. In this paper, we address incorporating memory processes with LLMs for generating cross-task robot actions, while the robot effectively switches between tasks. Our "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.13505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-18T13:38:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2f8bd8bdf2042952fb925a52250da52b47cb7ea67b8f46c71bf334d4077b6ef","abstract_canon_sha256":"13d6cbd576c8b1d1cdccafdc56ba082abb49fa1c300d5a66cb3ab1bb2d630a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:11.463147Z","signature_b64":"if+o/yhDHP2LKxXs6NLRN8DIBDm0915Qq6dpi3a0IQ0XG1LXwYOkn1G3QC+yBicUYSWK8ZWLBXrVh/Ewvb7WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8597fbc94c63ea5b219666926b168f9557ec028e0c86b65af7d6be11294c071a","last_reissued_at":"2026-07-05T09:19:11.462652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:11.462652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Burak Can Kaplan, Carlo Mazzola, Giulia Belgiovine, Hassan Ali, Luk\\'a\\v{s} Gajdo\\v{s}ech, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-07-18T13:38:21Z","abstract_excerpt":"Large Language Models (LLMs) have been recently used in robot applications for grounding LLM common-sense reasoning with the robot's perception and physical abilities. In humanoid robots, memory also plays a critical role in fostering real-world embodiment and facilitating long-term interactive capabilities, especially in multi-task setups where the robot must remember previous task states, environment states, and executed actions. In this paper, we address incorporating memory processes with LLMs for generating cross-task robot actions, while the robot effectively switches between tasks. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13505","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.13505/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.13505","created_at":"2026-07-05T09:19:11.462711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13505v2","created_at":"2026-07-05T09:19:11.462711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13505","created_at":"2026-07-05T09:19:11.462711+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWL7XSKMMPVF","created_at":"2026-07-05T09:19:11.462711+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWL7XSKMMPVFWIMW","created_at":"2026-07-05T09:19:11.462711+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWL7XSKM","created_at":"2026-07-05T09:19:11.462711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20373","citing_title":"CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV","json":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV.json","graph_json":"https://pith.science/api/pith-number/QWL7XSKMMPVFWIMWM2JGWFUPSV/graph.json","events_json":"https://pith.science/api/pith-number/QWL7XSKMMPVFWIMWM2JGWFUPSV/events.json","paper":"https://pith.science/paper/QWL7XSKM"},"agent_actions":{"view_html":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV","download_json":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV.json","view_paper":"https://pith.science/paper/QWL7XSKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13505&json=true","fetch_graph":"https://pith.science/api/pith-number/QWL7XSKMMPVFWIMWM2JGWFUPSV/graph.json","fetch_events":"https://pith.science/api/pith-number/QWL7XSKMMPVFWIMWM2JGWFUPSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV/action/storage_attestation","attest_author":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV/action/author_attestation","sign_citation":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV/action/citation_signature","submit_replication":"https://pith.science/pith/QWL7XSKMMPVFWIMWM2JGWFUPSV/action/replication_record"}},"created_at":"2026-07-05T09:19:11.462711+00:00","updated_at":"2026-07-05T09:19:11.462711+00:00"}