{"paper":{"title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Faroq AL-Tam, Jie M. Zhang, Muhammad Al-Qurishi, Shuyin Ouyang, Zhaozhi Qian","submitted_at":"2026-05-16T22:18:04Z","abstract_excerpt":"Reinforcement Learning (RL) is an important paradigm for aligning Diffusion Language Models (DLMs) toward functional correctness in code generation. However, these models often encounter a ``capability cliff'' on complex tasks, where execution-based semantic rewards become too low to provide a viable learning signal. In this paper, we present a systematic empirical study of RL post-training for diffusion-based code generation along three axes: reward design, hint-conditioned sampling, and task difficulty. We investigate the effectiveness of execution-free rewards as alternatives to traditional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17174","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/2605.17174/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.751160Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.974772Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b5cc19cd54d77ae96335ac2e55c2a75010d708f29bfad0ed72a756a37f0049b9"},"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"}