{"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/marg-multi-agent-review-generation-for","title":"MARG: Multi-Agent Review Generation for Scientific Papers","arxiv_id":"2401.04259","date":"2024-01-08","proceeding":null,"authors":["Mike D'Arcy","Tom Hope","Larry Birnbaum","Doug Downey"],"abstract":"We study the ability of LLMs to generate feedback for scientific papers and develop MARG, a feedback generation approach using multiple LLM instances that engage in internal discussion. By distributing paper text across agents, MARG can consume the full text of papers beyond the input length limitations of the base LLM, and by specializing agents and incorporating sub-tasks tailored to different comment types (experiments, clarity, impact) it improves the helpfulness and specificity of feedback. In a user study, baseline methods using GPT-4 were rated as producing generic or very generic comments more than half the time, and only 1.7 comments per paper were rated as good overall in the best baseline. Our system substantially improves the ability of GPT-4 to generate specific and helpful feedback, reducing the rate of generic comments from 60% to 29% and generating 3.7 good comments per paper (a 2.2x improvement).","url_abs":"https://arxiv.org/abs/2401.04259v1","url_pdf":"https://arxiv.org/pdf/2401.04259v1.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":"marg-multi-agent-review-generation-for","repo_url":"https://github.com/allenai/marg-reviewer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"review-generation","task_name":"Review Generation"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.04259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04259"}},"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/allenai/marg-reviewer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":"5ebf094868fd0444","entry":"basic_token_align","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/edit.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/edit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5ebf094868fd0444"}},{"code_sha256_prefix":"6164eefcce2fb3e1","entry":"colorify","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/color.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/color.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6164eefcce2fb3e1"}},{"code_sha256_prefix":"28f1982db3388dba","entry":"downsample_recs","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/data.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"28f1982db3388dba"}},{"code_sha256_prefix":"00448a446842cc38","entry":"index_by","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/data.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00448a446842cc38"}},{"code_sha256_prefix":"7142219531463a02","entry":"openc","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/data.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7142219531463a02"}},{"code_sha256_prefix":"ab60b777a46febd1","entry":"raw_table2str","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/logging.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab60b777a46febd1"}},{"code_sha256_prefix":"74be48c9b4dc9c99","entry":"table2str","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/logging.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74be48c9b4dc9c99"}},{"code_sha256_prefix":"6b96792de473f699","entry":"colorprint","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/color.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/color.py","link_basis":"first_harvest_node","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":"6b96792de473f699"}},{"code_sha256_prefix":"519a75e4f9f6bd58","entry":"levenshtein_distance","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/edit.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/edit.py","link_basis":"first_harvest_node","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":"519a75e4f9f6bd58"}},{"code_sha256_prefix":"843af5ddd4587178","entry":"make_word_diff","repo":"allenai/marg-reviewer","repo_kind":"official","path":"review_worker/aries/util/edit.py","file_url":"https://github.com/allenai/marg-reviewer/blob/HEAD/review_worker/aries/util/edit.py","link_basis":"first_harvest_node","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":"843af5ddd4587178"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}