{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WZYNFRJN7SCNY5KOC66MWPMOUW","short_pith_number":"pith:WZYNFRJN","schema_version":"1.0","canonical_sha256":"b670d2c52dfc84dc754e17bccb3d8ea58ae4540de93cb0ced992ff3b66c5252f","source":{"kind":"arxiv","id":"2504.21716","version":1},"attestation_state":"computed","paper":{"title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Marc Glocker, Markus Vincze, Matthias Hirschmanner, Peter H\\\"onig","submitted_at":"2025-04-30T15:00:20Z","abstract_excerpt":"We present an embodied robotic system with an LLM-driven agent-orchestration architecture for autonomous household object management. The system integrates memory-augmented task planning, enabling robots to execute high-level user commands while tracking past actions. It employs three specialized agents: a routing agent, a task planning agent, and a knowledge base agent, each powered by task-specific LLMs. By leveraging in-context learning, our system avoids the need for explicit model training. RAG enables the system to retrieve context from past interactions, enhancing long-term object track"},"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":"2504.21716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-30T15:00:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"abe22cdfcb4b12ee0771d842ca5e9ec81a55a7b43dc39efc949fbcc38b86585d","abstract_canon_sha256":"1fc85aecbf2686d2b42ae67cb7038a5385bd65b35022ca6191a328e77e3864e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:28.641748Z","signature_b64":"pVyjHg+fuydXd4xxY8OCdDtj2u1LcCLyodJAX1xYWHNxcvDEncvMXieF/9OPmpnSvsm0rOB/pOKH4Ao8WZk3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b670d2c52dfc84dc754e17bccb3d8ea58ae4540de93cb0ced992ff3b66c5252f","last_reissued_at":"2026-07-05T10:56:28.641269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:28.641269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Marc Glocker, Markus Vincze, Matthias Hirschmanner, Peter H\\\"onig","submitted_at":"2025-04-30T15:00:20Z","abstract_excerpt":"We present an embodied robotic system with an LLM-driven agent-orchestration architecture for autonomous household object management. The system integrates memory-augmented task planning, enabling robots to execute high-level user commands while tracking past actions. It employs three specialized agents: a routing agent, a task planning agent, and a knowledge base agent, each powered by task-specific LLMs. By leveraging in-context learning, our system avoids the need for explicit model training. RAG enables the system to retrieve context from past interactions, enhancing long-term object track"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21716","kind":"arxiv","version":1},"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/2504.21716/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":"2504.21716","created_at":"2026-07-05T10:56:28.641333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21716v1","created_at":"2026-07-05T10:56:28.641333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21716","created_at":"2026-07-05T10:56:28.641333+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZYNFRJN7SCN","created_at":"2026-07-05T10:56:28.641333+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZYNFRJN7SCNY5KO","created_at":"2026-07-05T10:56:28.641333+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZYNFRJN","created_at":"2026-07-05T10:56:28.641333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10927","citing_title":"AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16331","citing_title":"BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07594","citing_title":"MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":256,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09747","citing_title":"ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07594","citing_title":"MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW","json":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW.json","graph_json":"https://pith.science/api/pith-number/WZYNFRJN7SCNY5KOC66MWPMOUW/graph.json","events_json":"https://pith.science/api/pith-number/WZYNFRJN7SCNY5KOC66MWPMOUW/events.json","paper":"https://pith.science/paper/WZYNFRJN"},"agent_actions":{"view_html":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW","download_json":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW.json","view_paper":"https://pith.science/paper/WZYNFRJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21716&json=true","fetch_graph":"https://pith.science/api/pith-number/WZYNFRJN7SCNY5KOC66MWPMOUW/graph.json","fetch_events":"https://pith.science/api/pith-number/WZYNFRJN7SCNY5KOC66MWPMOUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW/action/storage_attestation","attest_author":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW/action/author_attestation","sign_citation":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW/action/citation_signature","submit_replication":"https://pith.science/pith/WZYNFRJN7SCNY5KOC66MWPMOUW/action/replication_record"}},"created_at":"2026-07-05T10:56:28.641333+00:00","updated_at":"2026-07-05T10:56:28.641333+00:00"}