{"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/dars-dynamic-action-re-sampling-to-enhance","title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","arxiv_id":"2503.14269","date":"2025-03-18","proceeding":null,"authors":["Vaibhav Aggarwal","Ojasv Kamal","Abhinav Japesh","Zhijing Jin","Bernhard Schölkopf"],"abstract":"Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents, that is faster and more effective at recovering from sub-optimal decisions compared to baselines. While traditional agents either follow linear trajectories or rely on random sampling for scaling compute, our approach DARS works by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt from that point. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2. Our framework achieves a pass@1 rate of 47%, outperforming state-of-the-art (SOTA) open-source frameworks.","url_abs":"https://arxiv.org/abs/2503.14269v1","url_pdf":"https://arxiv.org/pdf/2503.14269v1.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":"dars-dynamic-action-re-sampling-to-enhance","repo_url":"https://github.com/darsagent/dars-agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dars-dynamic-action-re-sampling-to-enhance","repo_url":"https://github.com/vaibhavagg303/dars-agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.14269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14269"}},"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/darsagent/dars-agent","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vaibhavagg303/dars-agent","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"2fad32f9ef6d9234","entry":"create_graph_from_tags","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/repograph/tags_to_graph.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/repograph/tags_to_graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2fad32f9ef6d9234"}},{"code_sha256_prefix":"f9a1693290545810","entry":"process_tag_file","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/repograph/update_tags.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/repograph/update_tags.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9a1693290545810"}},{"code_sha256_prefix":"34bc00c520ec6c8c","entry":"read_config","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/repograph/tags_to_graph.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/repograph/tags_to_graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34bc00c520ec6c8c"}},{"code_sha256_prefix":"52fb0d2d87bc8c00","entry":"read_config","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/repograph/update_tags.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/repograph/update_tags.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"52fb0d2d87bc8c00"}},{"code_sha256_prefix":"45f439e7f6c2efba","entry":"read_tags_from_json","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/repograph/tags_to_graph.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/repograph/tags_to_graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"45f439e7f6c2efba"}},{"code_sha256_prefix":"4426c4583f380e35","entry":"send_code_to_server","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/config/commands/_execute_ipython.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/config/commands/_execute_ipython.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4426c4583f380e35"}},{"code_sha256_prefix":"419d71560fa1c93a","entry":"send_command_to_server","repo":"darsagent/dars-agent","repo_kind":"official","path":"dars-agent/config/commands/_execute_server.py","file_url":"https://github.com/darsagent/dars-agent/blob/HEAD/dars-agent/config/commands/_execute_server.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"419d71560fa1c93a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}