{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NVLQFEDOYIFGOVRTZ3TC6RKXKW","short_pith_number":"pith:NVLQFEDO","canonical_record":{"source":{"id":"2504.16078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:57:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"362e3f0afc355fcd5e9484e2d8d324d6bcec6f10f2bb2f631f77d2f89d178584","abstract_canon_sha256":"fae69e75ceb51fae2914706b108509325b5530e06dd6dda4a655686084ca4d3a"},"schema_version":"1.0"},"canonical_sha256":"6d5702906ec20a675633cee62f455755855de36d2d05c2f25217f7ef50bf916d","source":{"kind":"arxiv","id":"2504.16078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16078","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16078v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16078","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"NVLQFEDOYIFG","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"NVLQFEDOYIFGOVRT","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"NVLQFEDO","created_at":"2026-07-05T10:52:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NVLQFEDOYIFGOVRTZ3TC6RKXKW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:57:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"362e3f0afc355fcd5e9484e2d8d324d6bcec6f10f2bb2f631f77d2f89d178584","abstract_canon_sha256":"fae69e75ceb51fae2914706b108509325b5530e06dd6dda4a655686084ca4d3a"},"schema_version":"1.0"},"canonical_sha256":"6d5702906ec20a675633cee62f455755855de36d2d05c2f25217f7ef50bf916d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:35.153539Z","signature_b64":"yj/MkBxa/vukIwkS+wyj5lwDkfmqM91R/0wmgv6ebDKXNq7tWWMgMv85Pk8IWYY38wBayOjyjzZZb9G+slvaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5702906ec20a675633cee62f455755855de36d2d05c2f25217f7ef50bf916d","last_reissued_at":"2026-07-05T10:52:35.153082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:35.153082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16078","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":"2026-07-05T10:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3vbp0CNoYn0ZGT4l3+knsKaMqrNMEkDnjDQFlLthtxkl0er+9Klx0jsTKSDT8rJjuBEkU0/kPqUQLAI86IlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:16:47.679647Z"},"content_sha256":"462a7982efac0ea0d94c71cb9ed12de2762612cbc14675ad952257d7b3d9044c","schema_version":"1.0","event_id":"sha256:462a7982efac0ea0d94c71cb9ed12de2762612cbc14675ad952257d7b3d9044c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NVLQFEDOYIFGOVRTZ3TC6RKXKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jordi Grau-Moya, J\\\"org Bornschein, Markus Wulfmeier, Razvan Pascanu, Thomas Schmied","submitted_at":"2025-04-22T17:57:14Z","abstract_excerpt":"The success of Large Language Models (LLMs) has sparked interest in various agentic applications. A key hypothesis is that LLMs, leveraging common sense and Chain-of-Thought (CoT) reasoning, can effectively explore and efficiently solve complex domains. However, LLM agents have been found to suffer from sub-optimal exploration and the knowing-doing gap, the inability to effectively act on knowledge present in the model. In this work, we systematically study why LLMs perform sub-optimally in decision-making scenarios. In particular, we closely examine three prevalent failure modes: greediness, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16078","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/2504.16078/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":"2026-07-05T10:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81Q68PDG2S77n2VZB4ncLN97SfwRA4bZx1fiIrRMQp0kxW4WmfZEW0g4LXJ/aH6esyo5wsfBR7H3VftKkr8tCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:16:47.680141Z"},"content_sha256":"a2471b4a4752ae5d83f4b22c5c95c6bbb46b067e61b67799510150b8bc8cecff","schema_version":"1.0","event_id":"sha256:a2471b4a4752ae5d83f4b22c5c95c6bbb46b067e61b67799510150b8bc8cecff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/bundle.json","state_url":"https://pith.science/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/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":"2026-08-08T19:16:47Z","links":{"resolver":"https://pith.science/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW","bundle":"https://pith.science/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/bundle.json","state":"https://pith.science/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVLQFEDOYIFGOVRTZ3TC6RKXKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NVLQFEDOYIFGOVRTZ3TC6RKXKW","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":"fae69e75ceb51fae2914706b108509325b5530e06dd6dda4a655686084ca4d3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:57:14Z","title_canon_sha256":"362e3f0afc355fcd5e9484e2d8d324d6bcec6f10f2bb2f631f77d2f89d178584"},"schema_version":"1.0","source":{"id":"2504.16078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16078","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16078v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16078","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"NVLQFEDOYIFG","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"NVLQFEDOYIFGOVRT","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"NVLQFEDO","created_at":"2026-07-05T10:52:35Z"}],"graph_snapshots":[{"event_id":"sha256:a2471b4a4752ae5d83f4b22c5c95c6bbb46b067e61b67799510150b8bc8cecff","target":"graph","created_at":"2026-07-05T10:52:35Z","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/2504.16078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of Large Language Models (LLMs) has sparked interest in various agentic applications. A key hypothesis is that LLMs, leveraging common sense and Chain-of-Thought (CoT) reasoning, can effectively explore and efficiently solve complex domains. However, LLM agents have been found to suffer from sub-optimal exploration and the knowing-doing gap, the inability to effectively act on knowledge present in the model. In this work, we systematically study why LLMs perform sub-optimally in decision-making scenarios. In particular, we closely examine three prevalent failure modes: greediness, ","authors_text":"Jordi Grau-Moya, J\\\"org Bornschein, Markus Wulfmeier, Razvan Pascanu, Thomas Schmied","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:57:14Z","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16078","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":"sha256:462a7982efac0ea0d94c71cb9ed12de2762612cbc14675ad952257d7b3d9044c","target":"record","created_at":"2026-07-05T10:52:35Z","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":"fae69e75ceb51fae2914706b108509325b5530e06dd6dda4a655686084ca4d3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:57:14Z","title_canon_sha256":"362e3f0afc355fcd5e9484e2d8d324d6bcec6f10f2bb2f631f77d2f89d178584"},"schema_version":"1.0","source":{"id":"2504.16078","kind":"arxiv","version":1}},"canonical_sha256":"6d5702906ec20a675633cee62f455755855de36d2d05c2f25217f7ef50bf916d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d5702906ec20a675633cee62f455755855de36d2d05c2f25217f7ef50bf916d","first_computed_at":"2026-07-05T10:52:35.153082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:35.153082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yj/MkBxa/vukIwkS+wyj5lwDkfmqM91R/0wmgv6ebDKXNq7tWWMgMv85Pk8IWYY38wBayOjyjzZZb9G+slvaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:35.153539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:462a7982efac0ea0d94c71cb9ed12de2762612cbc14675ad952257d7b3d9044c","sha256:a2471b4a4752ae5d83f4b22c5c95c6bbb46b067e61b67799510150b8bc8cecff"],"state_sha256":"f25d61d3709a26b16858e3b6da11c9d7a8909352aa067f23dd70c81a5c665f73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/TXkfIg2JFqHMWls9Fcwf3RG3HYqYpYuV8AwrSYSu7kR7tiRwrfLi+yEhU5tzR31BHInetvPNM2TAvzkystDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:16:47.684087Z","bundle_sha256":"3880146d9c4000dbeaa18a0b06135a02851f352e8acce0373d3d08b5aa772749"}}