{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G67634FR72VNON4CUDCF4ZRL7X","short_pith_number":"pith:G67634FR","canonical_record":{"source":{"id":"2605.18597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:07:44Z","cross_cats_sorted":[],"title_canon_sha256":"58464ece0a6562f4e7f49db69a4c026f6c4b16e92589e1c78495b0addf0b99fe","abstract_canon_sha256":"c830bf0becadda5fe8f62ece7f235858246c11107629e672cb48e58a85d46d90"},"schema_version":"1.0"},"canonical_sha256":"37bfedf0b1feaad73782a0c45e662bfdd51b720c77321cb3ea9029ddd5ee050b","source":{"kind":"arxiv","id":"2605.18597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18597","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18597v1","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18597","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"G67634FR72VN","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"G67634FR72VNON4C","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"G67634FR","created_at":"2026-05-20T00:06:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G67634FR72VNON4CUDCF4ZRL7X","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:07:44Z","cross_cats_sorted":[],"title_canon_sha256":"58464ece0a6562f4e7f49db69a4c026f6c4b16e92589e1c78495b0addf0b99fe","abstract_canon_sha256":"c830bf0becadda5fe8f62ece7f235858246c11107629e672cb48e58a85d46d90"},"schema_version":"1.0"},"canonical_sha256":"37bfedf0b1feaad73782a0c45e662bfdd51b720c77321cb3ea9029ddd5ee050b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:10.068448Z","signature_b64":"zyjGydVG4X4i07w+LS0GhbkN6IL50rdOEV3szRwe1UDbNPcxAMTWArEDnH/DbFW4MmtprmsMiij5EOpev19oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37bfedf0b1feaad73782a0c45e662bfdd51b720c77321cb3ea9029ddd5ee050b","last_reissued_at":"2026-05-20T00:06:10.067565Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:10.067565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18597","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":"2026-05-20T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eczAN+ds5hBMS/bRPfVD19Gxq5x2/cjLJSx+BU5WTXVEAgs81VxtwhiHVwzeP3leMyse1vskFmyG7NZ5Tcp1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:53:59.749963Z"},"content_sha256":"72f5d8e74ea5d88017d4d93823f44edd276b120ad82659e8f1ceaa58a839bb11","schema_version":"1.0","event_id":"sha256:72f5d8e74ea5d88017d4d93823f44edd276b120ad82659e8f1ceaa58a839bb11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G67634FR72VNON4CUDCF4ZRL7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Action Reparameterization for Efficient Agent Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bang Liu, Chenglin Wu, Cheng Yang, Fang Wu, Huaming Chen, Jiayi Zhang, Jiri Gesi, Qingwen Zeng, Qiyue Chen, Siru Ouyang, Wenhao Huang, Xiangru Tang, Yu Sun, Zijie Guo","submitted_at":"2026-05-18T16:07:44Z","abstract_excerpt":"Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through system-level optimizations or prompt engineering, we argue that a key bottleneck lies in the representation of the action space itself. We propose Latent Action Reparameterization (LAR), a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior. By reparameterizing agent actions into latent un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18597","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/2605.18597/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.263745Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"138023a8ec98b08ec6f56a07b9c1878ba7dce9bb86060d56113a52b18c5e2461"},"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":"2026-05-20T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cfxtB4VuumIwiBej8pDKVNvmM95nxMYCKQALy72UplWJY4uxxmdYDsH7H5DJVGrd8yOgv23uCKLyhv4iYumaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:53:59.750736Z"},"content_sha256":"b13b1621567e8f5ad4a7e07dc590d7249eb2b044fd7fb3bb0283faf6c58464b6","schema_version":"1.0","event_id":"sha256:b13b1621567e8f5ad4a7e07dc590d7249eb2b044fd7fb3bb0283faf6c58464b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G67634FR72VNON4CUDCF4ZRL7X/bundle.json","state_url":"https://pith.science/pith/G67634FR72VNON4CUDCF4ZRL7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G67634FR72VNON4CUDCF4ZRL7X/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":"2026-05-23T08:53:59Z","links":{"resolver":"https://pith.science/pith/G67634FR72VNON4CUDCF4ZRL7X","bundle":"https://pith.science/pith/G67634FR72VNON4CUDCF4ZRL7X/bundle.json","state":"https://pith.science/pith/G67634FR72VNON4CUDCF4ZRL7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G67634FR72VNON4CUDCF4ZRL7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G67634FR72VNON4CUDCF4ZRL7X","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":"c830bf0becadda5fe8f62ece7f235858246c11107629e672cb48e58a85d46d90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:07:44Z","title_canon_sha256":"58464ece0a6562f4e7f49db69a4c026f6c4b16e92589e1c78495b0addf0b99fe"},"schema_version":"1.0","source":{"id":"2605.18597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18597","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18597v1","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18597","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"G67634FR72VN","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"G67634FR72VNON4C","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"G67634FR","created_at":"2026-05-20T00:06:10Z"}],"graph_snapshots":[{"event_id":"sha256:b13b1621567e8f5ad4a7e07dc590d7249eb2b044fd7fb3bb0283faf6c58464b6","target":"graph","created_at":"2026-05-20T00:06:10Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.263745Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18597/integrity.json","findings":[],"snapshot_sha256":"138023a8ec98b08ec6f56a07b9c1878ba7dce9bb86060d56113a52b18c5e2461","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through system-level optimizations or prompt engineering, we argue that a key bottleneck lies in the representation of the action space itself. We propose Latent Action Reparameterization (LAR), a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior. By reparameterizing agent actions into latent un","authors_text":"Bang Liu, Chenglin Wu, Cheng Yang, Fang Wu, Huaming Chen, Jiayi Zhang, Jiri Gesi, Qingwen Zeng, Qiyue Chen, Siru Ouyang, Wenhao Huang, Xiangru Tang, Yu Sun, Zijie Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:07:44Z","title":"Latent Action Reparameterization for Efficient Agent Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18597","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":"sha256:72f5d8e74ea5d88017d4d93823f44edd276b120ad82659e8f1ceaa58a839bb11","target":"record","created_at":"2026-05-20T00:06:10Z","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":"c830bf0becadda5fe8f62ece7f235858246c11107629e672cb48e58a85d46d90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T16:07:44Z","title_canon_sha256":"58464ece0a6562f4e7f49db69a4c026f6c4b16e92589e1c78495b0addf0b99fe"},"schema_version":"1.0","source":{"id":"2605.18597","kind":"arxiv","version":1}},"canonical_sha256":"37bfedf0b1feaad73782a0c45e662bfdd51b720c77321cb3ea9029ddd5ee050b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37bfedf0b1feaad73782a0c45e662bfdd51b720c77321cb3ea9029ddd5ee050b","first_computed_at":"2026-05-20T00:06:10.067565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:10.067565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zyjGydVG4X4i07w+LS0GhbkN6IL50rdOEV3szRwe1UDbNPcxAMTWArEDnH/DbFW4MmtprmsMiij5EOpev19oCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:10.068448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72f5d8e74ea5d88017d4d93823f44edd276b120ad82659e8f1ceaa58a839bb11","sha256:b13b1621567e8f5ad4a7e07dc590d7249eb2b044fd7fb3bb0283faf6c58464b6"],"state_sha256":"2e723cd03f47ba75d20aaa8ad0e9f7b98637cd1d4902ead3fa169a6faf115214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odZAx1EQhoauS03X9W2WDVb6k5FbrUPC+Ac3HJhy1Ihg0ukdT1koh7avllxjKZXArgDL48olMYJT8CBykW+7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T08:53:59.755231Z","bundle_sha256":"be1467e85a0edd3ea2f6e0b571e79288cc745022847a828100fc6a5c4b97d2b9"}}