{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A4YI2J375WJRRNHU6DCBBGSGXT","short_pith_number":"pith:A4YI2J37","canonical_record":{"source":{"id":"2605.07926","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T15:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"298835dc23693e4627548307586cb086366c3bd4f1c2abdfeaf337fd1cc579e6","abstract_canon_sha256":"c7bd849a0bedf3ca53e795edddb5a69745ff9fd911a56ad5f4458166bcfdb295"},"schema_version":"1.0"},"canonical_sha256":"07308d277fed9318b4f4f0c4109a46bcdc086e6710acb73e1deee590fb307d83","source":{"kind":"arxiv","id":"2605.07926","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07926","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07926v2","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07926","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"A4YI2J375WJR","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"A4YI2J375WJRRNHU","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"A4YI2J37","created_at":"2026-05-21T01:05:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A4YI2J375WJRRNHU6DCBBGSGXT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.07926","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T15:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"298835dc23693e4627548307586cb086366c3bd4f1c2abdfeaf337fd1cc579e6","abstract_canon_sha256":"c7bd849a0bedf3ca53e795edddb5a69745ff9fd911a56ad5f4458166bcfdb295"},"schema_version":"1.0"},"canonical_sha256":"07308d277fed9318b4f4f0c4109a46bcdc086e6710acb73e1deee590fb307d83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:20.640350Z","signature_b64":"bGRe3A5D9PG1eqB7H1zQCCPeZFq49w4Vf7Xx1p6gSGRzWlTJNCVwt6TqHUbTjgnWIv1/1kjJQ23bXxiIH1MEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07308d277fed9318b4f4f0c4109a46bcdc086e6710acb73e1deee590fb307d83","last_reissued_at":"2026-05-21T01:05:20.639499Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:20.639499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.07926","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VW3OEolpAFdZmvGCvfioiqYCES15pGXiNNGS6QzgxROBN+hm+hY2kE8dHFyDck+c2FJ6sT09LjJFPI0fNCvyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:43:06.158759Z"},"content_sha256":"b0efa2e6cd64fef13c5c43c0badcc820eee4c8b31fd77057270db2229e27cd85","schema_version":"1.0","event_id":"sha256:b0efa2e6cd64fef13c5c43c0badcc820eee4c8b31fd77057270db2229e27cd85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A4YI2J375WJRRNHU6DCBBGSGXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongyu Ru, Jingwen Xv, Lin Qiu, Xiaohua Wang, Xiaoqing Zheng, Xiaoyu Li, Xuezhi Cao, Xunliang Cai, Yiyang Li, Zhengkang Guo","submitted_at":"2026-05-08T15:59:27Z","abstract_excerpt":"As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an escape-room-style benchmark that tests whether agents can infer, execute, and revise novel tool-use procedures under explicit long-range dependency constraints. Each task defines a directed acyclic dependency graph over tools and items, requiring agents to invoke real external functions, track hidden state revealed incrementally, propagate intermediate results, and submit a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments with sixteen LLM agents and human participants show that performance drops sharply as dependency depth increases: humans decline from 98.3% success at difficulty-5 to 80.0% at difficulty-25, while the best model drops from 90.0% to 60.0%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the escape-room tasks with explicit DAG constraints and incremental state revelation accurately capture the core challenges of out-of-domain tool-grounded reasoning without introducing benchmark-specific artifacts or overly artificial constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AgentEscapeBench shows LLM agents' success rates drop from 90% to 60% as tool-dependency depth increases from 5 to 25 steps, while humans drop only from 98% to 80%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ff43d7e8accb9131a0e7e9f3cc68309f3b9957f1d5d0312ae9631a92ed0e892d"},"source":{"id":"2605.07926","kind":"arxiv","version":2},"verdict":{"id":"442f6878-78d8-4d65-82e2-bb497f852b74","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T03:28:00.724118Z","strongest_claim":"Experiments with sixteen LLM agents and human participants show that performance drops sharply as dependency depth increases: humans decline from 98.3% success at difficulty-5 to 80.0% at difficulty-25, while the best model drops from 90.0% to 60.0%.","one_line_summary":"AgentEscapeBench shows LLM agents' success rates drop from 90% to 60% as tool-dependency depth increases from 5 to 25 steps, while humans drop only from 98% to 80%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the escape-room tasks with explicit DAG constraints and incremental state revelation accurately capture the core challenges of out-of-domain tool-grounded reasoning without introducing benchmark-specific artifacts or overly artificial constraints.","pith_extraction_headline":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07926/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:02:13.538218Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T04:46:14.043446Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:18.284052Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:23:49.029118Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ce6a8a5f131eeed6dd64df3e7607604f3ce61d7b9ee8ffaa994b1ff9aa314519"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"db7545589050c9d2a56954e6db12d4d5ea3a2ac4aa29e0852203ff552838724b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"442f6878-78d8-4d65-82e2-bb497f852b74"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4mYOH0YG+BRwpoXi39oLWNSK1Y1wqi3/hxru7cV3ZY3E/izwNdQn2NyX/XYwXAxlTJjxFFPjTylFOBR9KR8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:43:06.159360Z"},"content_sha256":"8a8f1c13e5c2e729fe716907f50b70aa481d2144b165daaf31384fcf6eba158e","schema_version":"1.0","event_id":"sha256:8a8f1c13e5c2e729fe716907f50b70aa481d2144b165daaf31384fcf6eba158e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4YI2J375WJRRNHU6DCBBGSGXT/bundle.json","state_url":"https://pith.science/pith/A4YI2J375WJRRNHU6DCBBGSGXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4YI2J375WJRRNHU6DCBBGSGXT/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":"2026-05-27T19:43:06Z","links":{"resolver":"https://pith.science/pith/A4YI2J375WJRRNHU6DCBBGSGXT","bundle":"https://pith.science/pith/A4YI2J375WJRRNHU6DCBBGSGXT/bundle.json","state":"https://pith.science/pith/A4YI2J375WJRRNHU6DCBBGSGXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4YI2J375WJRRNHU6DCBBGSGXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A4YI2J375WJRRNHU6DCBBGSGXT","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":"c7bd849a0bedf3ca53e795edddb5a69745ff9fd911a56ad5f4458166bcfdb295","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T15:59:27Z","title_canon_sha256":"298835dc23693e4627548307586cb086366c3bd4f1c2abdfeaf337fd1cc579e6"},"schema_version":"1.0","source":{"id":"2605.07926","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07926","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07926v2","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07926","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"A4YI2J375WJR","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"A4YI2J375WJRRNHU","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"A4YI2J37","created_at":"2026-05-21T01:05:20Z"}],"graph_snapshots":[{"event_id":"sha256:8a8f1c13e5c2e729fe716907f50b70aa481d2144b165daaf31384fcf6eba158e","target":"graph","created_at":"2026-05-21T01:05:20Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments with sixteen LLM agents and human participants show that performance drops sharply as dependency depth increases: humans decline from 98.3% success at difficulty-5 to 80.0% at difficulty-25, while the best model drops from 90.0% to 60.0%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the escape-room tasks with explicit DAG constraints and incremental state revelation accurately capture the core challenges of out-of-domain tool-grounded reasoning without introducing benchmark-specific artifacts or overly artificial constraints."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AgentEscapeBench shows LLM agents' success rates drop from 90% to 60% as tool-dependency depth increases from 5 to 25 steps, while humans drop only from 98% to 80%."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures."}],"snapshot_sha256":"ff43d7e8accb9131a0e7e9f3cc68309f3b9957f1d5d0312ae9631a92ed0e892d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"db7545589050c9d2a56954e6db12d4d5ea3a2ac4aa29e0852203ff552838724b"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T10:02:13.538218Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T04:46:14.043446Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:18.284052Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T11:23:49.029118Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.07926/integrity.json","findings":[],"snapshot_sha256":"ce6a8a5f131eeed6dd64df3e7607604f3ce61d7b9ee8ffaa994b1ff9aa314519","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an escape-room-style benchmark that tests whether agents can infer, execute, and revise novel tool-use procedures under explicit long-range dependency constraints. Each task defines a directed acyclic dependency graph over tools and items, requiring agents to invoke real external functions, track hidden state revealed incrementally, propagate intermediate results, and submit a","authors_text":"Dongyu Ru, Jingwen Xv, Lin Qiu, Xiaohua Wang, Xiaoqing Zheng, Xiaoyu Li, Xuezhi Cao, Xunliang Cai, Yiyang Li, Zhengkang Guo","cross_cats":[],"headline":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T15:59:27Z","title":"AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07926","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T03:28:00.724118Z","id":"442f6878-78d8-4d65-82e2-bb497f852b74","model_set":{"reader":"grok-4.3"},"one_line_summary":"AgentEscapeBench shows LLM agents' success rates drop from 90% to 60% as tool-dependency depth increases from 5 to 25 steps, while humans drop only from 98% to 80%.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LLM agents handle short tool sequences but lose substantial accuracy when required to track deep chains of dependencies across novel procedures.","strongest_claim":"Experiments with sixteen LLM agents and human participants show that performance drops sharply as dependency depth increases: humans decline from 98.3% success at difficulty-5 to 80.0% at difficulty-25, while the best model drops from 90.0% to 60.0%.","weakest_assumption":"That the escape-room tasks with explicit DAG constraints and incremental state revelation accurately capture the core challenges of out-of-domain tool-grounded reasoning without introducing benchmark-specific artifacts or overly artificial constraints."}},"verdict_id":"442f6878-78d8-4d65-82e2-bb497f852b74"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0efa2e6cd64fef13c5c43c0badcc820eee4c8b31fd77057270db2229e27cd85","target":"record","created_at":"2026-05-21T01:05:20Z","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":"c7bd849a0bedf3ca53e795edddb5a69745ff9fd911a56ad5f4458166bcfdb295","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T15:59:27Z","title_canon_sha256":"298835dc23693e4627548307586cb086366c3bd4f1c2abdfeaf337fd1cc579e6"},"schema_version":"1.0","source":{"id":"2605.07926","kind":"arxiv","version":2}},"canonical_sha256":"07308d277fed9318b4f4f0c4109a46bcdc086e6710acb73e1deee590fb307d83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07308d277fed9318b4f4f0c4109a46bcdc086e6710acb73e1deee590fb307d83","first_computed_at":"2026-05-21T01:05:20.639499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:20.639499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bGRe3A5D9PG1eqB7H1zQCCPeZFq49w4Vf7Xx1p6gSGRzWlTJNCVwt6TqHUbTjgnWIv1/1kjJQ23bXxiIH1MEAA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:20.640350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07926","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0efa2e6cd64fef13c5c43c0badcc820eee4c8b31fd77057270db2229e27cd85","sha256:8a8f1c13e5c2e729fe716907f50b70aa481d2144b165daaf31384fcf6eba158e"],"state_sha256":"a028393b51c0566952bde264ad744a2ab265960a85522352bb8b1e99d6164b79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQ4SbFtHDebPJCFKIZwVS+o3gx/vYqbXn1FkfcHLdoeKl2FwzM4nXL0JU9feV0aYmXl87nkwSc08mwgxcQboAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:43:06.162774Z","bundle_sha256":"49954b14c9ae44bbf81698a7f267ec61da5df8f48bcfcb6dcaa17fc45640ebf6"}}