{"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/xolver-multi-agent-reasoning-with-holistic","title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","arxiv_id":"2506.14234","date":"2025-06-17","proceeding":null,"authors":["Md Tanzib Hosain","Salman Rahman","Md Kishor Morol","Md Rizwan Parvez"],"abstract":"Despite impressive progress on complex reasoning, current large language models (LLMs) typically operate in isolation - treating each problem as an independent attempt, without accumulating or integrating experiential knowledge. In contrast, expert problem solvers - such as Olympiad or programming contest teams - leverage a rich tapestry of experiences: absorbing mentorship from coaches, developing intuition from past problems, leveraging knowledge of tool usage and library functionality, adapting strategies based on the expertise and experiences of peers, continuously refining their reasoning through trial and error, and learning from other related problems even during competition. We introduce Xolver, a training-free multi-agent reasoning framework that equips a black-box LLM with a persistent, evolving memory of holistic experience. Xolver integrates diverse experience modalities, including external and self-retrieval, tool use, collaborative interactions, agent-driven evaluation, and iterative refinement. By learning from relevant strategies, code fragments, and abstract reasoning patterns at inference time, Xolver avoids generating solutions from scratch - marking a transition from isolated inference toward experience-aware language agents. Built on both open-weight and proprietary models, Xolver consistently outperforms specialized reasoning agents. Even with lightweight backbones (e.g., QWQ-32B), it often surpasses advanced models including Qwen3-235B, Gemini 2.5 Pro, o3, and o4-mini-high. With o3-mini-high, it achieves new best results on GSM8K (98.1%), AIME'24 (94.4%), AIME'25 (93.7%), Math-500 (99.8%), and LiveCodeBench-V5 (91.6%) - highlighting holistic experience learning as a key step toward generalist agents capable of expert-level reasoning. Code and data are available at https://kagnlp.github.io/xolver.github.io/.","url_abs":"https://arxiv.org/abs/2506.14234v1","url_pdf":"https://arxiv.org/pdf/2506.14234v1.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":"xolver-multi-agent-reasoning-with-holistic","repo_url":"https://github.com/kagnlp/Xolver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-livecodebench","task":"Code Generation","dataset":"Livecodebench","model":"Xolver","rank_in_archive_order":1,"of":3,"metrics":{"Acc":"91.6"},"uses_additional_data":false},{"leaderboard":"/sota/gsm8k-on-gsm8k","task":"GSM8K","dataset":"GSM8K","model":"Xolver","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"98.1"},"uses_additional_data":false},{"leaderboard":"/sota/mathematical-reasoning-on-aime24","task":"Mathematical Reasoning","dataset":"AIME24","model":"Xolver","rank_in_archive_order":1,"of":9,"metrics":{"Acc":"94.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.14234","atlas_url":"https://app.syntology.ai/?focus=2506.14234","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":"2506.14234"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2506.14234\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2506.14234"},"call":"get_concepts_for_paper(arxiv_id=\"2506.14234\")"}],"by_repo":[{"repo":"kagnlp/Xolver","kind":"listed","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":"c8398bf119d70c006e62b07d078e53e96212e13c73b20ca8120effd851d67efe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}