{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z6XHRTTXQH727PGIKEVRGZSIYN","short_pith_number":"pith:Z6XHRTTX","schema_version":"1.0","canonical_sha256":"cfae78ce7781ffafbcc8512b136648c360833918f3aa5617a37270196cac35dd","source":{"kind":"arxiv","id":"2505.19761","version":1},"attestation_state":"computed","paper":{"title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlin Chen, Wei Liu, Xiangyu Yue, Xiaoye Qu, Yu Cheng, Zhi Wang, Zican Hu","submitted_at":"2025-05-26T09:43:40Z","abstract_excerpt":"While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-reward scenarios. Inspired by the divide-and-conquer principle, we propose an innovative framework **GLIDER** (**G**rounding **L**anguage Models as Eff**I**cient **D**ecision-Making Agents via Offline Hi**E**rarchical **R**einforcement Learning) that introduces a parameter-efficient and generally applicable hierarchy to LLM policies. We develop a scheme where the low-level controll"},"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":"2505.19761","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T09:43:40Z","cross_cats_sorted":[],"title_canon_sha256":"0a904148d3c093680eccf079e6287fc52242f6dbfc81bbf54bdccbd89760e25c","abstract_canon_sha256":"2ca1521d83aa702a6d4eb69d6b85b21975bbb8b07fc993d9417beda0e5bcb551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:35.765041Z","signature_b64":"khj5R3FhJdcXyA/DZJ7hG1hD259CZ/KycqWrWLD2hMvT6GL7qGyvPpWYN3D1mkBwLFOcNvZx3SSUopFcSFEgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfae78ce7781ffafbcc8512b136648c360833918f3aa5617a37270196cac35dd","last_reissued_at":"2026-07-05T11:09:35.764578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:35.764578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlin Chen, Wei Liu, Xiangyu Yue, Xiaoye Qu, Yu Cheng, Zhi Wang, Zican Hu","submitted_at":"2025-05-26T09:43:40Z","abstract_excerpt":"While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-reward scenarios. Inspired by the divide-and-conquer principle, we propose an innovative framework **GLIDER** (**G**rounding **L**anguage Models as Eff**I**cient **D**ecision-Making Agents via Offline Hi**E**rarchical **R**einforcement Learning) that introduces a parameter-efficient and generally applicable hierarchy to LLM policies. We develop a scheme where the low-level controll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19761","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/2505.19761/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":"2505.19761","created_at":"2026-07-05T11:09:35.764631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19761v1","created_at":"2026-07-05T11:09:35.764631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19761","created_at":"2026-07-05T11:09:35.764631+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6XHRTTXQH72","created_at":"2026-07-05T11:09:35.764631+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6XHRTTXQH727PGI","created_at":"2026-07-05T11:09:35.764631+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6XHRTTX","created_at":"2026-07-05T11:09:35.764631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00203","citing_title":"DeSQ: Decomposition-based SPARQL Query Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00977","citing_title":"HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents","ref_index":19,"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":226,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01954","citing_title":"Moira: Language-driven Hierarchical Reinforcement Learning for Pair Trading","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN","json":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN.json","graph_json":"https://pith.science/api/pith-number/Z6XHRTTXQH727PGIKEVRGZSIYN/graph.json","events_json":"https://pith.science/api/pith-number/Z6XHRTTXQH727PGIKEVRGZSIYN/events.json","paper":"https://pith.science/paper/Z6XHRTTX"},"agent_actions":{"view_html":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN","download_json":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN.json","view_paper":"https://pith.science/paper/Z6XHRTTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19761&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6XHRTTXQH727PGIKEVRGZSIYN/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6XHRTTXQH727PGIKEVRGZSIYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN/action/storage_attestation","attest_author":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN/action/author_attestation","sign_citation":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN/action/citation_signature","submit_replication":"https://pith.science/pith/Z6XHRTTXQH727PGIKEVRGZSIYN/action/replication_record"}},"created_at":"2026-07-05T11:09:35.764631+00:00","updated_at":"2026-07-05T11:09:35.764631+00:00"}