{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/fea-bench-a-benchmark-for-evaluating","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","arxiv_id":"2503.06680","date":"2025-03-09","proceeding":null,"authors":["Wei Li","Xin Zhang","Zhongxin Guo","Shaoguang Mao","Wen Luo","Guangyue Peng","Yangyu Huang","Houfeng Wang","Scarlett Li"],"abstract":"Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with relevant unit test files to ensure that the solution can be verified. The feature implementation requires LLMs to simultaneously possess code completion capabilities for new components and code editing abilities for other relevant parts in the code repository, providing a more comprehensive evaluation method of LLMs' automated software engineering capabilities. Experimental results show that LLMs perform significantly worse in the FEA-Bench, highlighting considerable challenges in such repository-level incremental code development.","url_abs":"https://arxiv.org/abs/2503.06680v2","url_pdf":"https://arxiv.org/pdf/2503.06680v2.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":[],"tasks":[{"task_slug":"code-completion","task_name":"Code Completion"},{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06680"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/microsoft/FEA-Bench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":16},"by_repo_kind":{"found_in_text":{"samples":16,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ff2548d09259cc4f","entry":"add_lines","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/collect/make_instructions.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/collect/make_instructions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff2548d09259cc4f"}},{"code_sha256_prefix":"15fc850decd38c0e","entry":"add_lines_list","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/collect/make_instructions.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/collect/make_instructions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15fc850decd38c0e"}},{"code_sha256_prefix":"6a251b76292312e2","entry":"calc_cost","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/prediction_openai.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/prediction_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a251b76292312e2"}},{"code_sha256_prefix":"7eea2e9c7d73b624","entry":"call_chat","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/prediction_openai.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/prediction_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7eea2e9c7d73b624"}},{"code_sha256_prefix":"9a7e9f7c41d4f4e3","entry":"cl100k","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/collect/make_instructions.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/collect/make_instructions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a7e9f7c41d4f4e3"}},{"code_sha256_prefix":"9e041acdfbfb5dd6","entry":"find_matches","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/patch_process.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/patch_process.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e041acdfbfb5dd6"}},{"code_sha256_prefix":"211c8776b6934d53","entry":"get_default_branch","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/get_dataset.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/get_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"211c8776b6934d53"}},{"code_sha256_prefix":"fdb9a6e7c7dfd837","entry":"get_model_limits_huggingface","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/prediction_vllm.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/prediction_vllm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdb9a6e7c7dfd837"}},{"code_sha256_prefix":"3878579948b74212","entry":"get_tokenizer_online","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/tokenizer_online.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/tokenizer_online.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3878579948b74212"}},{"code_sha256_prefix":"dd9b2adb8a5ef900","entry":"gpt_tokenize","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/tokenizer_online.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/tokenizer_online.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd9b2adb8a5ef900"}},{"code_sha256_prefix":"cbd300cf44ebcf38","entry":"is_test_file","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/collect/utils.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/collect/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbd300cf44ebcf38"}},{"code_sha256_prefix":"050d848429c3c4b5","entry":"parse_hunk_header","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/patch_process.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/patch_process.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"050d848429c3c4b5"}},{"code_sha256_prefix":"266a34e05903a0dd","entry":"parse_model_args","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/run_prediction.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/run_prediction.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"266a34e05903a0dd"}},{"code_sha256_prefix":"85ea28b3cf26e6e6","entry":"process_datum_openai","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/prediction/prediction_openai.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/prediction/prediction_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85ea28b3cf26e6e6"}},{"code_sha256_prefix":"744a9f4f56892e94","entry":"remove_comments_and_whitespace","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/get_dataset.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/get_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"744a9f4f56892e94"}},{"code_sha256_prefix":"ae38c85f79ffb235","entry":"run_command","repo":"microsoft/FEA-Bench","repo_kind":"found_in_text","path":"feabench/get_dataset.py","file_url":"https://github.com/microsoft/FEA-Bench/blob/HEAD/feabench/get_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae38c85f79ffb235"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}