{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N77TD7SHJZBAPVZJLEYJTNWDAU","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":"b422e6da56b96c8b1bc8420cfa2324daf051b3915f2d37dfc2409487363f4e59","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T12:54:49Z","title_canon_sha256":"1f16a4226a071cdbf3f1cd05245bfa26c4805c95f951685733bca1f8ca43ef1d"},"schema_version":"1.0","source":{"id":"2506.00539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00539","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00539v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00539","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"N77TD7SHJZBA","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"N77TD7SHJZBAPVZJ","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"N77TD7SH","created_at":"2026-07-05T11:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:24be1f38ae73b17eaa865305a303174e8dd4a37468ca4d4e0f46c843525ea7b2","target":"graph","created_at":"2026-07-05T11:15:47Z","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/2506.00539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an exponentially large action space. Sampling actions in such a space can lead to extreme reward sparsity, which brings large reward variance, hindering effective reinforcement learning (RL). To address this, we propose ARIA, a method that Aggregates Rewards in Intention space ","authors_text":"Aili Chen, Deqing Yang, Jiangjie Chen, Ruihan Yang, Siyu Yuan, Xintao Wang, Yanghua Xiao, Yikai Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T12:54:49Z","title":"ARIA: Training Language Agents with Intention-Driven Reward Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00539","kind":"arxiv","version":2},"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":"sha256:71153d3cb599a93a5cea4fb1aaa30d4403128c5084d7e2d758f2b5314ee7caf4","target":"record","created_at":"2026-07-05T11:15:47Z","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":"b422e6da56b96c8b1bc8420cfa2324daf051b3915f2d37dfc2409487363f4e59","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T12:54:49Z","title_canon_sha256":"1f16a4226a071cdbf3f1cd05245bfa26c4805c95f951685733bca1f8ca43ef1d"},"schema_version":"1.0","source":{"id":"2506.00539","kind":"arxiv","version":2}},"canonical_sha256":"6fff31fe474e4207d729593099b6c3052b869732ba972d57c7e9723fbd629eae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fff31fe474e4207d729593099b6c3052b869732ba972d57c7e9723fbd629eae","first_computed_at":"2026-07-05T11:15:47.533574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:47.533574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fB1p8+Jkk9ejudkKLIDA35495L4CnEgW9O/qq7wysOxHSrgQd5304fEMKtXJMLcbks/GrWq0kBSVqv0+gZ96Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:47.534049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71153d3cb599a93a5cea4fb1aaa30d4403128c5084d7e2d758f2b5314ee7caf4","sha256:24be1f38ae73b17eaa865305a303174e8dd4a37468ca4d4e0f46c843525ea7b2"],"state_sha256":"816dbe317a3328fd41001287b5bb60c7dc69274405f4575aa545e1d2f14d874b"}