{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/execution-guided-line-by-line-code-generation","title":"Execution Guided Line-by-Line Code Generation","arxiv_id":"2506.10948","date":"2025-06-12","proceeding":null,"authors":["Boaz Lavon","Shahar Katz","Lior Wolf"],"abstract":"We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process. While large language models (LLMs) have demonstrated impressive code generation capabilities, they typically do not utilize execution feedback during inference, a critical signal that human programmers regularly leverage. Our method, Execution-Guided Classifier-Free Guidance (EG-CFG), dynamically incorporates execution signals as the model generates code, providing line-by-line feedback that guides the generation process toward executable solutions. EG-CFG employs a multi-stage process: first, we conduct beam search to sample candidate program completions for each line; second, we extract execution signals by executing these candidates against test cases; and finally, we incorporate these signals into the prompt during generation. By maintaining consistent signals across tokens within the same line and refreshing signals at line boundaries, our approach provides coherent guidance while preserving syntactic structure. Moreover, the method naturally supports native parallelism at the task level in which multiple agents operate in parallel, exploring diverse reasoning paths and collectively generating a broad set of candidate solutions. Our experiments across diverse coding tasks demonstrate that EG-CFG significantly improves code generation performance compared to standard approaches, achieving state-of-the-art results across various levels of complexity, from foundational problems to challenging competitive programming tasks. Our code is available at: https://github.com/boazlavon/eg_cfg","url_abs":"https://arxiv.org/abs/2506.10948v1","url_pdf":"https://arxiv.org/pdf/2506.10948v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"execution-guided-line-by-line-code-generation","repo_url":"https://github.com/boazlavon/eg_cfg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-codecontests","task":"Code Generation","dataset":"CodeContests","model":"EG-CFG (DeepSeek-V3-0324)","rank_in_archive_order":1,"of":8,"metrics":{"Test Set pass@1":"58.18"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-humaneval","task":"Code Generation","dataset":"HumanEval","model":"EG-CFG (DeepSeek-V3-0324)","rank_in_archive_order":5,"of":8,"metrics":{"Pass@1":"96.95"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-humaneval-et","task":"Code Generation","dataset":"HumanEval-ET","model":"EG-CFG (DeepSeek-V3-0324)","rank_in_archive_order":1,"of":2,"metrics":{"Pass@1":"87.19"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"EG-CFG (DeepSeek-V3-0324)","rank_in_archive_order":1,"of":99,"metrics":{"Accuracy":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"EG-CFG (DeepSeek Coder 1.3b Instruct)","rank_in_archive_order":16,"of":99,"metrics":{"Accuracy":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp-et","task":"Code Generation","dataset":"MBPP-ET","model":"EG-CFG (DeepSeek-V3-0324)","rank_in_archive_order":1,"of":2,"metrics":{"Pass@1":"73.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.10948","atlas_url":"https://app.syntology.ai/?focus=2506.10948","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2506.10948"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2506.10948\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2506.10948"},"call":"get_concepts_for_paper(arxiv_id=\"2506.10948\")"}],"by_repo":[{"repo":"boazlavon/eg_cfg","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b04f98a5e32d99000cec0ffc7cbc66e82bf777597db791b7aa2ebf8ce8e93706","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}