{"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/swe-bench-cl-continual-learning-for-coding","title":"SWE-Bench-CL: Continual Learning for Coding Agents","arxiv_id":"2507.00014","date":"2025-06-13","proceeding":null,"authors":["Thomas Joshi","Shayan Chowdhury","Fatih Uysal"],"abstract":"Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce SWE-Bench-CL, a novel continual learning benchmark built on the human-verified SWE-Bench Verified dataset introduced by OpenAI and Princeton-NLP in 2024. By organizing GitHub issues into chronologically ordered sequences that reflect natural repository evolution, SWE-Bench-CL enables direct evaluation of an agent's ability to accumulate experience, transfer knowledge across tasks, and resist catastrophic forgetting. We complement the dataset with (i) a preliminary analysis of inter-task structural similarity and contextual sensitivity, (ii) an interactive LangGraph-based evaluation framework augmented with a FAISS-backed semantic memory module, and (iii) a suite of specialized continual learning metrics -- including average accuracy, forgetting, forward/backward transfer, tool-use efficiency, and a generalized Composite Continual Learning Score and CL-F-beta score -- to capture the stability-plasticity trade-off. We outline a rigorous experimental protocol comparing memory-enabled and memory-disabled agents across diverse Python repositories. All code and data are publicly available at https://github.com/thomasjoshi/agents-never-forget, providing the community with a reproducible platform for developing more adaptive and robust AI agents in software engineering.","url_abs":"https://arxiv.org/abs/2507.00014v1","url_pdf":"https://arxiv.org/pdf/2507.00014v1.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":"swe-bench-cl-continual-learning-for-coding","repo_url":"https://github.com/thomasjoshi/agents-never-forget","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2507.00014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.00014"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomasjoshi/agents-never-forget","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"303acf42ea51afb7","entry":"calculate_levenshtein_distance","repo":"thomasjoshi/agents-never-forget","repo_kind":"official","path":"eval_v1/analysis.py","file_url":"https://github.com/thomasjoshi/agents-never-forget/blob/HEAD/eval_v1/analysis.py","link_basis":"first_harvest_node","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":"303acf42ea51afb7"}},{"code_sha256_prefix":"c49f36d21e1a7bc9","entry":"get_current_commit","repo":"thomasjoshi/agents-never-forget","repo_kind":"official","path":"eval_v2_agent/eval_procedure.py","file_url":"https://github.com/thomasjoshi/agents-never-forget/blob/HEAD/eval_v2_agent/eval_procedure.py","link_basis":"first_harvest_node","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":"c49f36d21e1a7bc9"}},{"code_sha256_prefix":"8fbf533433a94b7d","entry":"load_or_initialize_state","repo":"thomasjoshi/agents-never-forget","repo_kind":"official","path":"eval_v1/eval_procedure.py","file_url":"https://github.com/thomasjoshi/agents-never-forget/blob/HEAD/eval_v1/eval_procedure.py","link_basis":"first_harvest_node","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":"8fbf533433a94b7d"}},{"code_sha256_prefix":"8f76660febbbdff5","entry":"setup_repository","repo":"thomasjoshi/agents-never-forget","repo_kind":"official","path":"eval_v2_agent/eval_procedure.py","file_url":"https://github.com/thomasjoshi/agents-never-forget/blob/HEAD/eval_v2_agent/eval_procedure.py","link_basis":"first_harvest_node","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":"8f76660febbbdff5"}},{"code_sha256_prefix":"3a2d093e98a59ef5","entry":"setup_swe_bench","repo":"thomasjoshi/agents-never-forget","repo_kind":"official","path":"eval_v1/eval_procedure.py","file_url":"https://github.com/thomasjoshi/agents-never-forget/blob/HEAD/eval_v1/eval_procedure.py","link_basis":"first_harvest_node","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":"3a2d093e98a59ef5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}