Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

AgentTuning: Enabling Generalized Agent Abilities for LLMs (2023)
Lemur: Harmonizing Natural Language and Code for Language Agents (2023)
FireAct: Toward Language Agent Fine-tuning (2023)
HeaP: Hierarchical Policies for Web Actions using LLMs (2023)
Agent Instructs Large Language Models to be General Zero-Shot Reasoners (2023)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

\n","updatedAt":"2023-11-14T15:31:11.699Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7315371632575989},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[{"reaction":"👍","users":["yuchenlin","here789"],"count":2}],"isReport":false}},{"id":"6665477247613a01ee1ee91a","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false},"createdAt":"2024-06-09T06:10:58.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"# Building Better Language Agents: Lumos and Open-Source LLMs\n\nhttps://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/l9x-LE2Rz3GywOEjhYhO4.mp4 \n\n## Links 🔗:\n👉 Subscribe: https://www.youtube.com/@Arxflix\n👉 Twitter: https://x.com/arxflix\n👉 LMNT (Partner): https://lmnt.com/\n\n\nBy Arxflix\n![9t4iCUHx_400x400-1.jpg](https://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/v4S5zBurs0ouGNwYj1GEd.jpeg)","html":"

\n\t\n\t\t\n\t\n\t\n\t\tBuilding Better Language Agents: Lumos and Open-Source LLMs\n\t\n

\n\n

\n\t\n\t\t\n\t\n\t\n\t\tLinks 🔗:\n\t\n

👉 Subscribe: https://www.youtube.com/@Arxflix
👉 Twitter: https://x.com/arxflix
👉 LMNT (Partner): https://lmnt.com/

By Arxflix
$\"9t4iCUHx_400x400-1.jpg\"$

\n","updatedAt":"2024-06-09T06:10:58.121Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.48489609360694885},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2311.05657","authors":[{"_id":"65518d2efd13d5b5ec9f1204","user":{"_id":"634e4670a51d5df8c2d92fce","avatarUrl":"/avatars/c52d7150b4de6a2eb2d83b345d35cbc2.svg","isPro":false,"fullname":"Da Yin","user":"DaYin","type":"user"},"name":"Da Yin","status":"claimed_verified","statusLastChangedAt":"2023-11-13T08:49:37.015Z","hidden":false},{"_id":"65518d2efd13d5b5ec9f1205","user":{"_id":"65282b8d578679aac7888aec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65282b8d578679aac7888aec/dibBkhH-z1c70mJZZxJ7u.jpeg","isPro":false,"fullname":"Faeze Brahman","user":"faezeb","type":"user"},"name":"Faeze Brahman","status":"admin_assigned","statusLastChangedAt":"2023-11-13T08:42:38.020Z","hidden":false},{"_id":"65518d2efd13d5b5ec9f1206","user":{"_id":"6349886c429608888c42319a","avatarUrl":"/avatars/f84b5fe8b76172878274754e3399d6ec.svg","isPro":false,"fullname":"Abhilasha Ravichander","user":"lasha-nlp","type":"user"},"name":"Abhilasha Ravichander","status":"admin_assigned","statusLastChangedAt":"2023-11-13T08:42:45.888Z","hidden":false},{"_id":"65518d2efd13d5b5ec9f1207","name":"Khyathi Chandu","hidden":false},{"_id":"65518d2efd13d5b5ec9f1208","user":{"_id":"60b7b9d71b90c5d07c23fbd0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1622653364258-noauth.jpeg","isPro":false,"fullname":"Kai-Wei Chang","user":"kaiweichang","type":"user"},"name":"Kai-Wei Chang","status":"admin_assigned","statusLastChangedAt":"2023-11-13T08:43:27.324Z","hidden":false},{"_id":"65518d2efd13d5b5ec9f1209","user":{"_id":"64d42729f63b01b7f676b176","avatarUrl":"/avatars/52e54bdd6a1fb6c774a40cd70f3d7925.svg","isPro":false,"fullname":"Yejin Choi","user":"yejinchoinka","type":"user"},"name":"Yejin Choi","status":"admin_assigned","statusLastChangedAt":"2023-11-13T08:43:35.645Z","hidden":false},{"_id":"65518d2efd13d5b5ec9f120a","user":{"_id":"607f666a4ad99100d63ce35c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/607f666a4ad99100d63ce35c/QxhxnvfeV6efkxwUFHwjI.png","isPro":false,"fullname":"Bill Yuchen Lin","user":"yuchenlin","type":"user"},"name":"Bill Yuchen Lin","status":"claimed_verified","statusLastChangedAt":"2023-11-13T08:31:31.883Z","hidden":false}],"publishedAt":"2023-11-09T00:30:13.000Z","submittedOnDailyAt":"2023-11-13T00:12:54.583Z","title":"Lumos: Learning Agents with Unified Data, Modular Design, and\n Open-Source LLMs","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"We introduce Lumos, a novel framework for training language agents that\nemploys a unified data format and a modular architecture based on open-source\nlarge language models (LLMs). Lumos consists of three distinct modules:\nplanning, grounding, and execution. The planning module breaks down a task into\na series of high-level, tool-agnostic subgoals, which are then made specific by\nthe grounding module through a set of low-level actions. These actions are\nsubsequently executed by the execution module, utilizing a range of\noff-the-shelf tools and APIs. In order to train these modules effectively,\nhigh-quality annotations of subgoals and actions were collected and are made\navailable for fine-tuning open-source LLMs for various tasks such as complex\nquestion answering, web tasks, and math problems. Leveraging this unified data\nand modular design, Lumos not only achieves comparable or superior performance\nto current, state-of-the-art agents, but also exhibits several key advantages:\n(1) Lumos surpasses GPT-4/3.5-based agents in complex question answering and\nweb tasks, while equalling the performance of significantly larger LLM agents\non math tasks; (2) Lumos outperforms open-source agents created through\nconventional training methods and those using chain-of-thoughts training; and\n(3) Lumos is capable of effectively generalizing to unseen interactive tasks,\noutperforming larger LLM-based agents and even exceeding performance of\nspecialized agents.","upvotes":30,"discussionId":"65518d2efd13d5b5ec9f121f","githubRepo":"https://github.com/allenai/lumos","githubRepoAddedBy":"auto","ai_summary":"Lumos, a modular language agent framework using open-source LLMs, achieves superior performance across various tasks and demonstrates enhanced generalization.","ai_keywords":["language agents","open-source large language models","LLMs","planning module","grounding module","execution module","subgoals","low-level actions","fine-tuning","complex question answering","web tasks","math problems","chain-of-thoughts training","interactive tasks","specialized agents"],"githubStars":473},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64522233ea94bf023430dd95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/CVDqDeJ_fLTULhCTTSogb.png","isPro":true,"fullname":"Chenhui Zhang","user":"danielz01","type":"user"},{"_id":"607f666a4ad99100d63ce35c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/607f666a4ad99100d63ce35c/QxhxnvfeV6efkxwUFHwjI.png","isPro":false,"fullname":"Bill Yuchen Lin","user":"yuchenlin","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"608b8bb39d7c9519b4adae19","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1621947938344-noauth.png","isPro":true,"fullname":"Abubakar Abid","user":"abidlabs","type":"user"},{"_id":"6550ad5ff908d2479a73fc32","avatarUrl":"/avatars/72552db28a09578f99b05153647d64c5.svg","isPro":false,"fullname":"Dhinesh","user":"Dhineshdine","type":"user"},{"_id":"6438c7e7d221ff12edb18c0a","avatarUrl":"/avatars/9cd6bf51056def1a0cc3159a9fc854af.svg","isPro":false,"fullname":"Prashanth","user":"prashiyn","type":"user"},{"_id":"63653b1e25aa3bd177d06f8b","avatarUrl":"/avatars/405eb83d5171f90f6cc00da4d51a28ab.svg","isPro":false,"fullname":"Federico Minutoli","user":"DiTo97","type":"user"},{"_id":"62a3bb1cd0d8c2c2169f0b88","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62a3bb1cd0d8c2c2169f0b88/eT2TS0IlQbZtz-F_zHLz9.jpeg","isPro":true,"fullname":"Joseph [open/acc] Pollack","user":"Tonic","type":"user"},{"_id":"6426e84498a5be164d3a6533","avatarUrl":"/avatars/864a5f6ce9d86c72d12d030bd8fe55ff.svg","isPro":false,"fullname":"Bruno de Melo","user":"BdMelo","type":"user"},{"_id":"644825fcab5c7251886f8133","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/v0c8agQk9GqEymPjL-2gx.png","isPro":false,"fullname":"AnnabelleHe","user":"Annabiubiu","type":"user"},{"_id":"64f6562512c53650bf5d3b04","avatarUrl":"/avatars/c3b0ec9584dc198b818a93e31b49c389.svg","isPro":false,"fullname":"n","user":"vinamra2004","type":"user"},{"_id":"616d8baa25e22505064d248d","avatarUrl":"/avatars/58a8b5049d67294ce36e59989e74189a.svg","isPro":false,"fullname":"VLA","user":"Qwoook","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2311.05657

Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs

Published on Nov 9, 2023

· Submitted by

AK on Nov 13, 2023

Upvote

Authors:

Da Yin ,

Faeze Brahman ,

Abhilasha Ravichander ,

Kai-Wei Chang ,

Yejin Choi ,

Bill Yuchen Lin

Abstract

Lumos, a modular language agent framework using open-source LLMs, achieves superior performance across various tasks and demonstrates enhanced generalization.

AI-generated summary

We introduce Lumos, a novel framework for training language agents that employs a unified data format and a modular architecture based on open-source large language models (LLMs). Lumos consists of three distinct modules: planning, grounding, and execution. The planning module breaks down a task into a series of high-level, tool-agnostic subgoals, which are then made specific by the grounding module through a set of low-level actions. These actions are subsequently executed by the execution module, utilizing a range of off-the-shelf tools and APIs. In order to train these modules effectively, high-quality annotations of subgoals and actions were collected and are made available for fine-tuning open-source LLMs for various tasks such as complex question answering, web tasks, and math problems. Leveraging this unified data and modular design, Lumos not only achieves comparable or superior performance to current, state-of-the-art agents, but also exhibits several key advantages: (1) Lumos surpasses GPT-4/3.5-based agents in complex question answering and web tasks, while equalling the performance of significantly larger LLM agents on math tasks; (2) Lumos outperforms open-source agents created through conventional training methods and those using chain-of-thoughts training; and (3) Lumos is capable of effectively generalizing to unseen interactive tasks, outperforming larger LLM-based agents and even exceeding performance of specialized agents.