{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AHLYPIB676LZ7FPBW42KWQX6QJ","short_pith_number":"pith:AHLYPIB6","schema_version":"1.0","canonical_sha256":"01d787a03eff979f95e1b734ab42fe824c2843c35348f9ab525f918ee0b25b56","source":{"kind":"arxiv","id":"2602.02711","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Dynamic mixed-precision routing lets LLMs switch between high and low precision at each step to cut costs while keeping task success high.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huanrui Yang, Jianing Deng, Jingtong Hu, Song Wang, Tianlong Chen, Yuanzhe Li","submitted_at":"2026-02-02T19:24:04Z","abstract_excerpt":"Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While practitioners commonly believe a higher task success rate necessitates the use of a larger and stronger LLM model, multi-step interaction with a large LLM incurs prohibitive inference cost.\n  To address this problem, we explore the use of low-precision quantized LLMs in the long-horizon decision-making process. Based on the observation of diverse sensitivities among interaction steps, we propose Dynamic Mixed-Precision Routing (DMR), a f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2602.02711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T19:24:04Z","cross_cats_sorted":[],"title_canon_sha256":"9e76903305cc455099b14a0575d466670ccb1769da4f3de4950c4d9498cd9c12","abstract_canon_sha256":"a26ad1ed1c403a87ece0a993f16bb7fcfa2f2cd47b79106611db98be4126430c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.088944Z","signature_b64":"bDFaGQ0XWDTYwwmdcpMv3BXrFIucVNcBR38d/qmBrZqX7870qkeJe5bZSDFjUufACKKdMx7f1TQrU7PVgoKsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01d787a03eff979f95e1b734ab42fe824c2843c35348f9ab525f918ee0b25b56","last_reissued_at":"2026-05-17T23:39:00.088347Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.088347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Dynamic mixed-precision routing lets LLMs switch between high and low precision at each step to cut costs while keeping task success high.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huanrui Yang, Jianing Deng, Jingtong Hu, Song Wang, Tianlong Chen, Yuanzhe Li","submitted_at":"2026-02-02T19:24:04Z","abstract_excerpt":"Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While practitioners commonly believe a higher task success rate necessitates the use of a larger and stronger LLM model, multi-step interaction with a large LLM incurs prohibitive inference cost.\n  To address this problem, we explore the use of low-precision quantized LLMs in the long-horizon decision-making process. Based on the observation of diverse sensitivities among interaction steps, we propose Dynamic Mixed-Precision Routing (DMR), a f"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on ALFWorld and WebShop demonstrate that our approach achieves a strong accuracy-cost trade-off over single-precision baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The observation that interaction steps have diverse sensitivities to precision allows a router to be trained that reliably selects the right precision level without harming overall task success.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DMR uses a router trained in two stages (KL-divergence supervision then GRPO) to pick high or low precision LLMs per step, delivering better accuracy-cost trade-offs than fixed-precision baselines on ALFWorld and WebShop.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dynamic mixed-precision routing lets LLMs switch between high and low precision at each step to cut costs while keeping task success high.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0cab96d6ac0b07af14e1e5a4908ba364d2a65dbde47c058901cbabd74cf20275"},"source":{"id":"2602.02711","kind":"arxiv","version":2},"verdict":{"id":"e67e2e07-e25d-4b79-8827-dadc1b5f6d3d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:52:44.077711Z","strongest_claim":"Experiments on ALFWorld and WebShop demonstrate that our approach achieves a strong accuracy-cost trade-off over single-precision baselines.","one_line_summary":"DMR uses a router trained in two stages (KL-divergence supervision then GRPO) to pick high or low precision LLMs per step, delivering better accuracy-cost trade-offs than fixed-precision baselines on ALFWorld and WebShop.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The observation that interaction steps have diverse sensitivities to precision allows a router to be trained that reliably selects the right precision level without harming overall task success.","pith_extraction_headline":"Dynamic mixed-precision routing lets LLMs switch between high and low precision at each step to cut costs while keeping task success high."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"72ddd5294c4e2f5fc1657334bc660c5bca43a59e53677028fc119b6f052bad21"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.02711","created_at":"2026-05-17T23:39:00.088434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02711v2","created_at":"2026-05-17T23:39:00.088434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02711","created_at":"2026-05-17T23:39:00.088434+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHLYPIB676LZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHLYPIB676LZ7FPB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHLYPIB6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ","json":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ.json","graph_json":"https://pith.science/api/pith-number/AHLYPIB676LZ7FPBW42KWQX6QJ/graph.json","events_json":"https://pith.science/api/pith-number/AHLYPIB676LZ7FPBW42KWQX6QJ/events.json","paper":"https://pith.science/paper/AHLYPIB6"},"agent_actions":{"view_html":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ","download_json":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ.json","view_paper":"https://pith.science/paper/AHLYPIB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/AHLYPIB676LZ7FPBW42KWQX6QJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AHLYPIB676LZ7FPBW42KWQX6QJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ/action/storage_attestation","attest_author":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ/action/author_attestation","sign_citation":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ/action/citation_signature","submit_replication":"https://pith.science/pith/AHLYPIB676LZ7FPBW42KWQX6QJ/action/replication_record"}},"created_at":"2026-05-17T23:39:00.088434+00:00","updated_at":"2026-05-17T23:39:00.088434+00:00"}