{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6XHRTTXQH727PGIKEVRGZSIYN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2ca1521d83aa702a6d4eb69d6b85b21975bbb8b07fc993d9417beda0e5bcb551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T09:43:40Z","title_canon_sha256":"0a904148d3c093680eccf079e6287fc52242f6dbfc81bbf54bdccbd89760e25c"},"schema_version":"1.0","source":{"id":"2505.19761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19761","created_at":"2026-07-05T11:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19761v1","created_at":"2026-07-05T11:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19761","created_at":"2026-07-05T11:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"Z6XHRTTXQH72","created_at":"2026-07-05T11:09:35Z"},{"alias_kind":"pith_short_16","alias_value":"Z6XHRTTXQH727PGI","created_at":"2026-07-05T11:09:35Z"},{"alias_kind":"pith_short_8","alias_value":"Z6XHRTTX","created_at":"2026-07-05T11:09:35Z"}],"graph_snapshots":[{"event_id":"sha256:28794b3e63a248dc3c8f7514a1bbfd5348f88245d7e0e970703c026bd3ca0c73","target":"graph","created_at":"2026-07-05T11:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.19761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunlin Chen, Wei Liu, Xiangyu Yue, Xiaoye Qu, Yu Cheng, Zhi Wang, Zican Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T09:43:40Z","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19761","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a9fb972eae32688694557b7add54898388fded40258c440db3ec5177392d22d9","target":"record","created_at":"2026-07-05T11:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2ca1521d83aa702a6d4eb69d6b85b21975bbb8b07fc993d9417beda0e5bcb551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T09:43:40Z","title_canon_sha256":"0a904148d3c093680eccf079e6287fc52242f6dbfc81bbf54bdccbd89760e25c"},"schema_version":"1.0","source":{"id":"2505.19761","kind":"arxiv","version":1}},"canonical_sha256":"cfae78ce7781ffafbcc8512b136648c360833918f3aa5617a37270196cac35dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfae78ce7781ffafbcc8512b136648c360833918f3aa5617a37270196cac35dd","first_computed_at":"2026-07-05T11:09:35.764578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:35.764578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"khj5R3FhJdcXyA/DZJ7hG1hD259CZ/KycqWrWLD2hMvT6GL7qGyvPpWYN3D1mkBwLFOcNvZx3SSUopFcSFEgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:35.765041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9fb972eae32688694557b7add54898388fded40258c440db3ec5177392d22d9","sha256:28794b3e63a248dc3c8f7514a1bbfd5348f88245d7e0e970703c026bd3ca0c73"],"state_sha256":"5aba6451d3d38824976ea73899fa0d6bb9437420a818bb6846dc1a0a890f3b74"}