{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHO5UWCSVLPC556ND3UJOFEBOE","short_pith_number":"pith:GHO5UWCS","canonical_record":{"source":{"id":"2608.03502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:44:07Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"98262045dab1d8241f564e2c3f326c06b392528627bd02c293ae96a92900fd7a","abstract_canon_sha256":"13750035f4dcfe187fa860ec88882c8aff76f7f0e302a322d6a4c60e8f3de1c0"},"schema_version":"1.0"},"canonical_sha256":"31ddda5852aade2ef7cd1ee897148171176d8f1cee9cb23571a2420886787ab2","source":{"kind":"arxiv","id":"2608.03502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03502","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03502v1","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03502","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_12","alias_value":"GHO5UWCSVLPC","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_16","alias_value":"GHO5UWCSVLPC556N","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_8","alias_value":"GHO5UWCS","created_at":"2026-08-05T01:35:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHO5UWCSVLPC556ND3UJOFEBOE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:44:07Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"98262045dab1d8241f564e2c3f326c06b392528627bd02c293ae96a92900fd7a","abstract_canon_sha256":"13750035f4dcfe187fa860ec88882c8aff76f7f0e302a322d6a4c60e8f3de1c0"},"schema_version":"1.0"},"canonical_sha256":"31ddda5852aade2ef7cd1ee897148171176d8f1cee9cb23571a2420886787ab2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:58.575184Z","signature_b64":"hWDf6t8mJRh/+lPwzr/tmXWRriV2v+0jNxljqL8xCeMlGc8eTP4mJbbDut0TUzpVqEZ/AyAX5Tw4uAH+P/YsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ddda5852aade2ef7cd1ee897148171176d8f1cee9cb23571a2420886787ab2","last_reissued_at":"2026-08-05T01:35:58.573593Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:58.573593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03502","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T01:35:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrTQL+AbPWhOx454MbOte6nMwG54/4GWNoBOUzjkcTVa8xjKTboscusCmBVkI/xPWgNdM+gDJSOC/PEKipaqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:30:07.032322Z"},"content_sha256":"b252e0fddaae9f515f2842d96cbda0e672f171e4b3c6882b420729c3d704f308","schema_version":"1.0","event_id":"sha256:b252e0fddaae9f515f2842d96cbda0e672f171e4b3c6882b420729c3d704f308"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHO5UWCSVLPC556ND3UJOFEBOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Christophe D. Hounwanou, John Emeka Eze, Ya\\'e Ulrich Gaba","submitted_at":"2026-08-04T11:44:07Z","abstract_excerpt":"Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon sequential decision tasks that require precise action optimization and environment interaction. Reinforcement Learning (RL), while effective for sequential control, often lacks the high-level abstraction and task decomposition abilities needed for complex scenarios. This paper introduces an LLM-Augmented Reinforcement Learning Agent that integrates LLM-driven planning with RL-based action optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03502","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/2608.03502/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T01:35:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CndnCdlEEIOxRwtiC93wO3EhEan1Xigb221IgDwLgPr0I5U/YwN0oHVHWsGDGIfRwt8Dxm1DXeFXJKt/s/P7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:30:07.032657Z"},"content_sha256":"a172e06c39b7ff15b8e6fae246258767843a43e494c7ea7ff52fc8ffaa901667","schema_version":"1.0","event_id":"sha256:a172e06c39b7ff15b8e6fae246258767843a43e494c7ea7ff52fc8ffaa901667"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHO5UWCSVLPC556ND3UJOFEBOE/bundle.json","state_url":"https://pith.science/pith/GHO5UWCSVLPC556ND3UJOFEBOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHO5UWCSVLPC556ND3UJOFEBOE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T18:30:07Z","links":{"resolver":"https://pith.science/pith/GHO5UWCSVLPC556ND3UJOFEBOE","bundle":"https://pith.science/pith/GHO5UWCSVLPC556ND3UJOFEBOE/bundle.json","state":"https://pith.science/pith/GHO5UWCSVLPC556ND3UJOFEBOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHO5UWCSVLPC556ND3UJOFEBOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHO5UWCSVLPC556ND3UJOFEBOE","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":"13750035f4dcfe187fa860ec88882c8aff76f7f0e302a322d6a4c60e8f3de1c0","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:44:07Z","title_canon_sha256":"98262045dab1d8241f564e2c3f326c06b392528627bd02c293ae96a92900fd7a"},"schema_version":"1.0","source":{"id":"2608.03502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03502","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03502v1","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03502","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_12","alias_value":"GHO5UWCSVLPC","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_16","alias_value":"GHO5UWCSVLPC556N","created_at":"2026-08-05T01:35:58Z"},{"alias_kind":"pith_short_8","alias_value":"GHO5UWCS","created_at":"2026-08-05T01:35:58Z"}],"graph_snapshots":[{"event_id":"sha256:a172e06c39b7ff15b8e6fae246258767843a43e494c7ea7ff52fc8ffaa901667","target":"graph","created_at":"2026-08-05T01:35:58Z","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/2608.03502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon sequential decision tasks that require precise action optimization and environment interaction. Reinforcement Learning (RL), while effective for sequential control, often lacks the high-level abstraction and task decomposition abilities needed for complex scenarios. This paper introduces an LLM-Augmented Reinforcement Learning Agent that integrates LLM-driven planning with RL-based action optimiz","authors_text":"Christophe D. Hounwanou, John Emeka Eze, Ya\\'e Ulrich Gaba","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:44:07Z","title":"Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03502","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:b252e0fddaae9f515f2842d96cbda0e672f171e4b3c6882b420729c3d704f308","target":"record","created_at":"2026-08-05T01:35:58Z","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":"13750035f4dcfe187fa860ec88882c8aff76f7f0e302a322d6a4c60e8f3de1c0","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:44:07Z","title_canon_sha256":"98262045dab1d8241f564e2c3f326c06b392528627bd02c293ae96a92900fd7a"},"schema_version":"1.0","source":{"id":"2608.03502","kind":"arxiv","version":1}},"canonical_sha256":"31ddda5852aade2ef7cd1ee897148171176d8f1cee9cb23571a2420886787ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31ddda5852aade2ef7cd1ee897148171176d8f1cee9cb23571a2420886787ab2","first_computed_at":"2026-08-05T01:35:58.573593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:58.573593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hWDf6t8mJRh/+lPwzr/tmXWRriV2v+0jNxljqL8xCeMlGc8eTP4mJbbDut0TUzpVqEZ/AyAX5Tw4uAH+P/YsBQ==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:58.575184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b252e0fddaae9f515f2842d96cbda0e672f171e4b3c6882b420729c3d704f308","sha256:a172e06c39b7ff15b8e6fae246258767843a43e494c7ea7ff52fc8ffaa901667"],"state_sha256":"6a463ac5b97fcd7bf6fdb86eb569b8913f7f1310de09b96b2d2199a03ae8fcf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"keeUzLFycBNpWmTTM9iMadMJyq5wlmnmZEPCyim/fznHsgLMn2iHV5all9Z9UE+ulh2rLAx7xENQL3tbc61aCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:30:07.035875Z","bundle_sha256":"086bd7b39cb7fffd96362afc2d9936df35c9a7ae5ba67cf405745905062d6397"}}