{"paper":{"title":"PCTD: Preference-Guided Counterfactual Task Decomposition for Agent Tool Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chu Zhao, Fei Huang, Guibing Guo, Jianzhe Zhao, Lei Tang, Minghang Li, Yuanyuan Zhao, Zhengzong Chen","submitted_at":"2026-07-17T07:15:41Z","abstract_excerpt":"Task decomposition aims to transform ambiguous instructions into executable atomic subtasks, thereby guiding high-precision tool retrieval. However, our analysis reveals that directly adopting tool retrieval metrics, i.e., Recall or NDCG, as rewards for task decomposition can easily induce reward hacking in reinforcement learning-based methods. Specifically, models tend to maximize retrieval matching through strategies such as repetitive decomposition. This spurious correlation between the shallow features of decomposition results and retrieval metric impairs generalization in Out-of-Domain (O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15696","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/2607.15696/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"}