{"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/nexussum-hierarchical-llm-agents-for-long","title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","arxiv_id":"2505.24575","date":"2025-05-30","proceeding":null,"authors":["Hyuntak Kim","Byung-Hak Kim"],"abstract":"Summarizing long-form narratives--such as books, movies, and TV scripts--requires capturing intricate plotlines, character interactions, and thematic coherence, a task that remains challenging for existing LLMs. We introduce NexusSum, a multi-agent LLM framework for narrative summarization that processes long-form text through a structured, sequential pipeline--without requiring fine-tuning. Our approach introduces two key innovations: (1) Dialogue-to-Description Transformation: A narrative-specific preprocessing method that standardizes character dialogue and descriptive text into a unified format, improving coherence. (2) Hierarchical Multi-LLM Summarization: A structured summarization pipeline that optimizes chunk processing and controls output length for accurate, high-quality summaries. Our method establishes a new state-of-the-art in narrative summarization, achieving up to a 30.0% improvement in BERTScore (F1) across books, movies, and TV scripts. These results demonstrate the effectiveness of multi-agent LLMs in handling long-form content, offering a scalable approach for structured summarization in diverse storytelling domains.","url_abs":"https://arxiv.org/abs/2505.24575v1","url_pdf":"https://arxiv.org/pdf/2505.24575v1.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":"descriptive","task_name":"Descriptive"},{"task_slug":"form","task_name":"Form"},{"task_slug":"long-form-narrative-summarization","task_name":"Long-Form Narrative Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-form-narrative-summarization-on-booksum","task":"Long-Form Narrative Summarization","dataset":"BookSum","model":"NexusSum (Mistral Large)","rank_in_archive_order":1,"of":10,"metrics":{"BERTScore (F1)":"70.70","ROUGE (geometric mean of 1/2/L)":"18.27","ROUGE-1":"42.51","ROUGE-2":"10.27","ROUGE-L":"23.91"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-booksum","task":"Long-Form Narrative Summarization","dataset":"BookSum","model":"Zero-Shot (Mistral Large)","rank_in_archive_order":6,"of":10,"metrics":{"BERTScore (F1)":"46.42","ROUGE-1":"19.63","ROUGE-2":"2.99","ROUGE-L":"12.0"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-booksum","task":"Long-Form Narrative Summarization","dataset":"BookSum","model":"NexusSum (Claude 3 Haiku)","rank_in_archive_order":8,"of":10,"metrics":{"ROUGE (geometric mean of 1/2/L)":"16.46"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","task":"Long-Form Narrative Summarization","dataset":"MENSA","model":"NexusSum (Mistral Large)","rank_in_archive_order":1,"of":10,"metrics":{"BERTScore (F1)":"65.73","ROUGE-1":"44.91","ROUGE-2":"11.43","ROUGE-L":"19.23"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","task":"Long-Form Narrative Summarization","dataset":"MENSA","model":"Zero-Shot (Mistral Large)","rank_in_archive_order":8,"of":10,"metrics":{"BERTScore (F1)":"54.80","ROUGE-1":"37.43","ROUGE-2":"10.52","ROUGE-L":"21.52"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-moviesum","task":"Long-Form Narrative Summarization","dataset":"MovieSum","model":"NexusSum (Mistral Large)","rank_in_archive_order":1,"of":5,"metrics":{"BERTScore (F1)":"63.53","ROUGE-1":"44.91","ROUGE-2":"11.43","ROUGE-L":"19.23"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on-moviesum","task":"Long-Form Narrative Summarization","dataset":"MovieSum","model":"Zero-Shot (Mistral Large)","rank_in_archive_order":5,"of":5,"metrics":{"BERTScore (F1)":"55.50","ROUGE-1":"39.22","ROUGE-2":"10.53","ROUGE-L":"22.55"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on","task":"Long-Form Narrative Summarization","dataset":"SummScreen","model":"NexusSum (Mistral Large)","rank_in_archive_order":1,"of":5,"metrics":{"BERTScore (F1)":"61.59","ROUGE-1":"30.44","ROUGE-2":"6.40","ROUGE-L":"17.95"},"uses_additional_data":false},{"leaderboard":"/sota/long-form-narrative-summarization-on","task":"Long-Form Narrative Summarization","dataset":"SummScreen","model":"Zero-Shot (Mistral Large)","rank_in_archive_order":5,"of":5,"metrics":{"BERTScore (F1)":"57.23","ROUGE-1":"29.18","ROUGE-2":"7.43","ROUGE-L":"19.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.24575","atlas_url":"https://app.syntology.ai/?focus=2505.24575","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":"2505.24575"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2505.24575\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2505.24575"},"call":"get_concepts_for_paper(arxiv_id=\"2505.24575\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5bef58df0d4181c6208ceac7043886c23e4bb72afbcb8cebb5bd7783a5326b4b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}