From 8ef4098a1f2d6f946c512416f002bb6049e49d11 Mon Sep 17 00:00:00 2001 From: Nadeem Shabir Date: Fri, 20 Oct 2023 01:46:59 +0100 Subject: [PATCH 01/25] NadeemAgent entering the arena (#5824) Co-authored-by: Silen Naihin --- arena/NadeemAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/NadeemAgent.json diff --git a/arena/NadeemAgent.json b/arena/NadeemAgent.json new file mode 100644 index 00000000..9898b7c1 --- /dev/null +++ b/arena/NadeemAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/kiyanwang/AutoGPT", + "timestamp": "2023-10-19T14:11:40.660035", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From 052802ff8d9354f23620eb8b6a5fd68cda7e5c0e Mon Sep 17 00:00:00 2001 From: MittenCrab <404856145@qq.com> Date: Fri, 20 Oct 2023 08:48:01 +0800 Subject: [PATCH 02/25] zhizhi entering the arena (#5821) Co-authored-by: Silen Naihin --- arena/zhizhi.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/zhizhi.json diff --git a/arena/zhizhi.json b/arena/zhizhi.json new file mode 100644 index 00000000..58d86008 --- /dev/null +++ b/arena/zhizhi.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/bolyage/zhizhi", + "timestamp": "2023-10-19T11:38:51.332966", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From 17d93421e7a9315720c69ccdc41a35ff8c10ebe2 Mon Sep 17 00:00:00 2001 From: hunteraraujo Date: Thu, 19 Oct 2023 22:13:15 -0700 Subject: [PATCH 03/25] Add flutter_markdown dependency --- frontend/pubspec.lock | 24 ++++++++++++++++++++++++ frontend/pubspec.yaml | 1 + 2 files changed, 25 insertions(+) diff --git a/frontend/pubspec.lock b/frontend/pubspec.lock index 8b12578c..145d8393 100644 --- a/frontend/pubspec.lock +++ b/frontend/pubspec.lock @@ -9,6 +9,14 @@ packages: url: "https://pub.dev" source: hosted version: "1.3.6" + args: + dependency: transitive + description: + name: args + sha256: eef6c46b622e0494a36c5a12d10d77fb4e855501a91c1b9ef9339326e58f0596 + url: "https://pub.dev" + source: hosted + version: "2.4.2" async: dependency: transitive description: @@ -182,6 +190,14 @@ packages: url: "https://pub.dev" source: hosted version: "2.0.2" + flutter_markdown: + dependency: "direct main" + description: + name: flutter_markdown + sha256: "8afc9a6aa6d8e8063523192ba837149dbf3d377a37c0b0fc579149a1fbd4a619" + url: "https://pub.dev" + source: hosted + version: "0.6.18" flutter_test: dependency: "direct dev" description: flutter @@ -296,6 +312,14 @@ packages: url: "https://pub.dev" source: hosted version: "2.1.0" + markdown: + dependency: transitive + description: + name: markdown + sha256: acf35edccc0463a9d7384e437c015a3535772e09714cf60e07eeef3a15870dcd + url: "https://pub.dev" + source: hosted + version: "7.1.1" matcher: dependency: transitive description: diff --git a/frontend/pubspec.yaml b/frontend/pubspec.yaml index 2b3f39ff..bb2214ea 100644 --- a/frontend/pubspec.yaml +++ b/frontend/pubspec.yaml @@ -47,6 +47,7 @@ dependencies: uuid: ^4.0.0 url_launcher: ^6.1.14 fluttertoast: ^8.2.2 + flutter_markdown: ^0.6.18 dev_dependencies: flutter_test: From 9219bfba0e028a557109b8e39c0fd91c1df243f8 Mon Sep 17 00:00:00 2001 From: hunteraraujo Date: Thu, 19 Oct 2023 22:19:09 -0700 Subject: [PATCH 04/25] add Markdown detection and rendering - Implement `containsMarkdown` function to identify messages with Markdown - Utilize `flutter_markdown` package to render detected Markdown content - Enhance chat UI to conditionally display plain text or formatted Markdown --- .../lib/views/chat/agent_message_tile.dart | 25 ++++++++++++++++--- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/frontend/lib/views/chat/agent_message_tile.dart b/frontend/lib/views/chat/agent_message_tile.dart index 0587175b..91226f71 100644 --- a/frontend/lib/views/chat/agent_message_tile.dart +++ b/frontend/lib/views/chat/agent_message_tile.dart @@ -3,6 +3,7 @@ import 'dart:convert'; import 'package:auto_gpt_flutter_client/models/chat.dart'; import 'package:auto_gpt_flutter_client/views/chat/json_code_snippet_view.dart'; import 'package:flutter/material.dart'; +import 'package:flutter_markdown/flutter_markdown.dart'; class AgentMessageTile extends StatefulWidget { final Chat chat; @@ -26,6 +27,23 @@ class _AgentMessageTileState extends State { String jsonString = jsonEncode(widget.chat.jsonResponse); int artifactsCount = widget.chat.artifacts.length; + bool containsMarkdown(String text) { + // Regular expression to detect Markdown patterns like headers, bold, links, etc. + final RegExp markdownPattern = RegExp( + r'(?:\*\*|__).*?(?:\*\*|__)|' + // Bold + r'(?:\*|_).*?(?:\*|_)|' + // Italic + r'\[.*?\]\(.*?\)|' + // Links + r'!\[.*?\]\(.*?\)|' + // Images + r'#{1,6}.*', // Headers + multiLine: true, + caseSensitive: false, + ); + + return markdownPattern.hasMatch(text); + } + + bool hasMarkdown = containsMarkdown(widget.chat.message); + return LayoutBuilder( builder: (context, constraints) { double chatViewWidth = constraints.maxWidth; @@ -62,10 +80,9 @@ class _AgentMessageTileState extends State { Expanded( child: Container( padding: const EdgeInsets.fromLTRB(0, 10, 20, 10), - child: Text( - widget.chat.message, - maxLines: null, - ), + child: hasMarkdown + ? Markdown(data: widget.chat.message) + : Text(widget.chat.message, maxLines: null), ), ), ElevatedButton( From 952f18137785184ca12e38aad005dba450c4ddb6 Mon Sep 17 00:00:00 2001 From: hunteraraujo Date: Fri, 20 Oct 2023 00:13:12 -0700 Subject: [PATCH 05/25] Stop continuous mode when agent returns isLast --- frontend/lib/viewmodels/chat_viewmodel.dart | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/frontend/lib/viewmodels/chat_viewmodel.dart b/frontend/lib/viewmodels/chat_viewmodel.dart index 2056c874..bd42964e 100644 --- a/frontend/lib/viewmodels/chat_viewmodel.dart +++ b/frontend/lib/viewmodels/chat_viewmodel.dart @@ -157,7 +157,7 @@ class ChatViewModel with ChangeNotifier { // Notify UI of the new chats notifyListeners(); - if (_isContinuousMode) { + if (_isContinuousMode && !executedStep.isLast) { print("Continuous Mode: Step $currentStep of $continuousModeSteps"); if (currentStep < continuousModeSteps) { sendChatMessage(null, From 27ff99a9a5da63e04a73a4e0de0f42fd05a616b2 Mon Sep 17 00:00:00 2001 From: hunteraraujo Date: Fri, 20 Oct 2023 00:15:20 -0700 Subject: [PATCH 06/25] Check for inline code blocks in agent step --- frontend/lib/views/chat/agent_message_tile.dart | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/frontend/lib/views/chat/agent_message_tile.dart b/frontend/lib/views/chat/agent_message_tile.dart index 91226f71..4639b76b 100644 --- a/frontend/lib/views/chat/agent_message_tile.dart +++ b/frontend/lib/views/chat/agent_message_tile.dart @@ -28,13 +28,14 @@ class _AgentMessageTileState extends State { int artifactsCount = widget.chat.artifacts.length; bool containsMarkdown(String text) { - // Regular expression to detect Markdown patterns like headers, bold, links, etc. + // Regular expression to detect Markdown patterns including code blocks. final RegExp markdownPattern = RegExp( r'(?:\*\*|__).*?(?:\*\*|__)|' + // Bold r'(?:\*|_).*?(?:\*|_)|' + // Italic r'\[.*?\]\(.*?\)|' + // Links r'!\[.*?\]\(.*?\)|' + // Images - r'#{1,6}.*', // Headers + r'#{1,6}.*|' + // Headers + r'`.*?`', // Inline Code Blocks multiLine: true, caseSensitive: false, ); From 2187f66149ffa4bb99f9ca6a11b592fe4d683791 Mon Sep 17 00:00:00 2001 From: hunteraraujo Date: Fri, 20 Oct 2023 00:20:46 -0700 Subject: [PATCH 07/25] Show error toast for 5xx error --- frontend/lib/views/chat/chat_view.dart | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/frontend/lib/views/chat/chat_view.dart b/frontend/lib/views/chat/chat_view.dart index 40117d9b..5d34bf52 100644 --- a/frontend/lib/views/chat/chat_view.dart +++ b/frontend/lib/views/chat/chat_view.dart @@ -144,6 +144,20 @@ class _ChatViewState extends State { "linear-gradient(to right, #dc1c13, #dc1c13)", textColor: Colors.white, fontSize: 16.0); + } else if (response is http.Response && + response.statusCode >= 500 && + response.statusCode < 600) { + Fluttertoast.showToast( + msg: "500 error: Something went wrong", + toastLength: Toast.LENGTH_LONG, + gravity: ToastGravity.TOP, + timeInSecForIosWeb: 5, + backgroundColor: Colors.red, + webPosition: "center", + webBgColor: + "linear-gradient(to right, #dc1c13, #dc1c13)", + textColor: Colors.white, + fontSize: 16.0); } } }, From dae6ee2c4719add830e291f4aeef471f635a7457 Mon Sep 17 00:00:00 2001 From: SwiftyOS Date: Fri, 20 Oct 2023 14:27:07 +0200 Subject: [PATCH 08/25] Removed unfinished tutorials --- autogpts/forge/README.md | 7 -- .../forge/tutorials/wip_004_benchmarking.md | 37 --------- .../tutorials/wip_005_adding_abilities.md | 59 -------------- .../forge/tutorials/wip_006_planning_loop.md | 80 ------------------- 4 files changed, 183 deletions(-) delete mode 100644 autogpts/forge/tutorials/wip_004_benchmarking.md delete mode 100644 autogpts/forge/tutorials/wip_005_adding_abilities.md delete mode 100644 autogpts/forge/tutorials/wip_006_planning_loop.md diff --git a/autogpts/forge/README.md b/autogpts/forge/README.md index 7e696b85..2e6840c4 100644 --- a/autogpts/forge/README.md +++ b/autogpts/forge/README.md @@ -22,10 +22,3 @@ The getting started [tutorial series](https://aiedge.medium.com/autogpt-forge-e3 4. [AutoGPT Forge: Crafting Intelligent Agent Logic](https://medium.com/@aiedge/autogpt-forge-crafting-intelligent-agent-logic-bc5197b14cb4) -Coming soon: - - -3. Interacting with and Benchmarking your Agent -4. Abilities -5. The Planning Loop -6. Memories diff --git a/autogpts/forge/tutorials/wip_004_benchmarking.md b/autogpts/forge/tutorials/wip_004_benchmarking.md deleted file mode 100644 index 68cbd3df..00000000 --- a/autogpts/forge/tutorials/wip_004_benchmarking.md +++ /dev/null @@ -1,37 +0,0 @@ -# Harnessing the Power of Test-Driven Development with AGBenchmark - -## Introduction -- Understanding Test-Driven Development (TDD) -- Importance of Benchmarking in Agent Development - -## Section 1: Introduction to AGBenchmark -- Overview of AGBenchmark -- Setting up AGBenchmark in the Forge Environment - -## Section 2: Benchmarking with AGBenchmark -- Understanding Benchmark Categories and Tests -- Using AGBenchmark Commands to List and Start Tests - -## Section 3: Writing Tests for Your Agent -- Creating Benchmark Tests -- Structuring Test Cases and Scenarios - -## Section 4: Running and Analyzing Benchmark Tests -- Executing Benchmark Tests using CLI -- Analyzing Benchmark Results and Feedback - -## Section 5: Continuous Benchmarking -- Integrating Benchmarking into Development Workflow -- Automating Benchmark Testing - -## Conclusion -- Recap of the Tutorial -- Enhancing Your Agent through Continuous Benchmarking - -## Additional Resources -- Links to AGBenchmark Documentation -- Community Forums and Discussions on Benchmarking - -## Appendix -- Troubleshooting Common Benchmarking Issues -- Glossary of Benchmarking Terms diff --git a/autogpts/forge/tutorials/wip_005_adding_abilities.md b/autogpts/forge/tutorials/wip_005_adding_abilities.md deleted file mode 100644 index 1ab4cf7e..00000000 --- a/autogpts/forge/tutorials/wip_005_adding_abilities.md +++ /dev/null @@ -1,59 +0,0 @@ -# Ability Acquisition: Enhancing Your Agent's Capabilities - -## Introduction -- Understanding the Importance of Ability Acquisition -- The Concept of Abilities in AutoGPT - -## Section 1: Identifying Necessary Abilities -- Analyzing the Requirements for Your Agent -- Categorizing Abilities: Core vs. Supplementary - -## Section 2: Developing Abilities for Your Agent -- Integrating Existing Abilities from the Forge -- Developing Custom Abilities: A Step-by-step Guide - -## Section 3: Implementing and Executing Abilities -- Utilizing the Agent Protocol for Ability Implementation -- Executing Abilities: Task and Step Execution -- Example: Developing and Executing an Ability using Task and Step Schemas - -## Section 4: Encoding Abilities in Prompts for LLM Selection -- Understanding the Concept of Prompt Engineering -- Strategies for Effective Ability Encoding in Prompts -- Practical Examples: Encoding Various Abilities in Prompts - -## Section 5: Testing and Debugging Abilities -- Employing Test-Driven Development for Ability Testing -- Debugging Common Issues in Ability Implementation - -## Conclusion -- Recap of the Tutorial -- Preparing Your Agent for Ability Integration and Enhancement - -## Additional Resources - -From **The Rise and Potential of Large Language Model Based Agents: A Survey** *Zhiheng Xi (Fudan University) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14497)] [[code](https://github.com/woooodyy/llm-agent-paper-list)] -### Research Papers -- [2023/07] **ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs.** *Yujia Qin et al. arXiv.* [[paper](https://arxiv.org/abs/2307.16789)] [[code](https://github.com/openbmb/toolbench)] [[dataset](https://paperswithcode.com/dataset/toolbench)] -- [2023/05] **Large Language Models as Tool Makers.** *Tianle Cai et al. arXiv.* [[paper](https://arxiv.org/abs/2305.17126)] [[code](https://github.com/ctlllll/llm-toolmaker)] -- [2023/05] **CREATOR: Disentangling Abstract and Concrete Reasonings of Large Language Models through Tool Creation.** *Cheng Qian et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14318)] -- [2023/04] **Tool Learning with Foundation Models.** *Yujia Qin et al. arXiv.* [[paper](https://arxiv.org/abs/2304.08354)] [[code](https://github.com/openbmb/bmtools)] -- [2023/04] **ChemCrow: Augmenting large-language models with chemistry tools.** *Andres M Bran (Laboratory of Artificial Chemical Intelligence, ISIC, EPFL) et al. arXiv.* [[paper](https://arxiv.org/abs/2304.05376)] [[code](https://github.com/ur-whitelab/chemcrow-public)] -- [2023/04] **GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information.** *Qiao Jin, Yifan Yang, Qingyu Chen, Zhiyong Lu. arXiv.* [[paper](https://arxiv.org/abs/2304.09667)] [[code](https://github.com/ncbi/GeneGPT)] -- [2023/04] **OpenAGI: When LLM Meets Domain Experts.** *Yingqiang Ge et al. arXiv.* [[paper](https://arxiv.org/abs/2304.04370)] [[code](https://github.com/agiresearch/openagi)] -- [2023/03] **HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face.** *Yongliang Shen et al. arXiv.* [[paper](https://arxiv.org/abs/2303.17580)] [[code](https://github.com/microsoft/JARVIS)] -- [2023/03] **Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.** *Chenfei Wu et al. arXiv.* [[paper](https://arxiv.org/abs/2303.04671)] [[code](https://github.com/microsoft/visual-chatgpt)] -- [2023/02] **Augmented Language Models: a Survey.** *Grégoire Mialon et al. arXiv.* [[paper](https://arxiv.org/abs/2302.07842)] -- [2023/02] **Toolformer: Language Models Can Teach Themselves to Use Tools.** *Timo Schick et al. arXiv.* [[paper](https://arxiv.org/abs/2302.04761)] -- [2022/05] **TALM: Tool Augmented Language Models.** *Aaron Parisi et al. arXiv.* [[paper](https://arxiv.org/abs/2205.12255)] -- [2022/05] **MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning.** *Ehud Karpas et al. arXiv.* [[paper](https://arxiv.org/abs/2205.00445)] -- [2022/04] **Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.** *Michael Ahn et al. arXiv.* [[paper](https://arxiv.org/abs/2204.01691)] -- [2021/12] **WebGPT: Browser-assisted question-answering with human feedback.** *Reiichiro Nakano et al. arXiv.* [[paper](https://arxiv.org/abs/2112.09332)] -- [2021/07] **Evaluating Large Language Models Trained on Code.** *Mark Chen et al. arXiv.* [[paper](https://arxiv.org/abs/2107.03374)] [[code](https://github.com/openai/human-eval)] - - - -## Appendix -- Examples of Ability Implementations -- Glossary of Ability-Related Terms - diff --git a/autogpts/forge/tutorials/wip_006_planning_loop.md b/autogpts/forge/tutorials/wip_006_planning_loop.md deleted file mode 100644 index cf254036..00000000 --- a/autogpts/forge/tutorials/wip_006_planning_loop.md +++ /dev/null @@ -1,80 +0,0 @@ -# Mastering the Agent Planning Loop: Strategies for Effective Development - -## Introduction -- Understanding the Agent Planning Loop -- Significance of Effective Planning in Agent Development - -## Section 1: Concepts of Agent Planning Loop -- The Structure of an Agent Planning Loop -- Key Components and Functions - -## Section 2: Developing an Effective Planning Strategy -- Setting Goals and Objectives -- Identifying Tasks and Steps within the Planning Loop - -## Section 3: Implementing the Planning Loop -- Coding the Planning Loop in the Forge Environment -- Utilizing the Agent Protocol APIs - -## Section 4: Testing and Optimization -- Test-Driven Development of the Planning Loop -- Optimizing the Planning Loop for Better Performance - -## Section 5: Best Practices -- Tips for Effective Planning Loop Implementation -- Common Pitfalls to Avoid - -## Conclusion -- Recap of the Tutorial -- Leveraging the Planning Loop for Advanced Agent Development - -## Additional Resources - -From **The Rise and Potential of Large Language Model Based Agents: A Survey** *Zhiheng Xi (Fudan University) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14497)] [[code](https://github.com/woooodyy/llm-agent-paper-list)] - -### Reasoning - -- [2023/05] **Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement.** *Zhiheng Xi (Fudan University) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14497)] [[code](https://github.com/woooodyy/self-polish)] - -- [2023-03] **Large Language Models are Zero-Shot Reasoners.** *Takeshi Kojima (The University of Tokyo) et al. arXiv.* [[paper](https://arxiv.org/abs/2205.11916)][[code](https://github.com/kojima-takeshi188/zero_shot_cot)] - -- [2023/03] **Self-Refine: Iterative Refinement with Self-Feedback.** *Aman Madaan (Carnegie Mellon University) et al. arXiv.* [[paper](https://arxiv.org/abs/2303.17651)] [[code](https://github.com/madaan/self-refine)] - -- [2022/05] **Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning.** *Antonia Creswell (DeepMind) et al. arXiv.* [[paper](https://arxiv.org/abs/2205.09712)] - -- [2022/03] **Self-Consistency Improves Chain of Thought Reasoning in Language Models.** *Xuezhi Wang(Google Research) et al. arXiv.* [[paper](https://arxiv.org/abs/2203.11171)] [[code](https://github.com/huggingface/transformers/tree/main/src/transformers/models/bart)] - -- [2022/01] **Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.** *Jason Wei (Google Research,) et al. arXiv.* [[paper](https://arxiv.org/abs/2201.11903)] - - -### Planning - -#### Plan formulation - -- [2023/05] **Tree of Thoughts: Deliberate Problem Solving with Large Language Models.** *Shunyu Yao (Princeton University) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.10601)] [[code](https://github.com/princeton-nlp/tree-of-thought-llm)] -- [2023/05] **Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents.** *Yue Wu(Carnegie Mellon University) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.02412)] -- [2023/05] **Reasoning with Language Model is Planning with World Model.** *Shibo Hao (UC San Diego) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14992)] [[code](https://github.com/Ber666/RAP)] -- [2023/05] **SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks.** *Bill Yuchen Lin (Allen Institute for Artificial Intelligence) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.17390)] [[code](https://github.com/yuchenlin/swiftsage)] -- [2023/04] **LLM+P: Empowering Large Language Models with Optimal Planning Proficiency.** *Bo Liu (University of Texas at Austin) et al. arXiv.* [[paper](https://arxiv.org/abs/2304.11477)] [[code](https://github.com/Cranial-XIX/llm-pddl)] -- [2023/03] **HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face.** *Yongliang Shen (Microsoft Research Asia) et al. arXiv.* [[paper](https://arxiv.org/abs/2303.17580)] [[code](https://github.com/microsoft/JARVIS)] -- [2023/02] **Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents.** *ZiHao Wang (Peking University) et al. arXiv.* [[paper](https://arxiv.org/abs/2302.01560)] [[code](https://github.com/CraftJarvis/MC-Planner)] -- [2022/05] **Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.** *Denny Zhou (Google Research) et al. arXiv.* [[paper](https://arxiv.org/abs/2205.10625)] -- [2022/05] **MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning.** *Ehud Karpas (AI21 Labs) et al. arXiv.* [[paper](https://arxiv.org/abs/2205.00445)] -- [2022/04] **Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.** *Michael Ahn (Robotics at Google) et al. arXiv.* [[paper](https://arxiv.org/abs/2204.01691)] -- [2023/05] **Agents: An Open-source Framework for Autonomous Language Agents.** Wangchunshu Zhou (AIWaves) et al. arXiv.* [[paper](https://arxiv.org/pdf/2309.07870.pdf)] [[code](https://github.com/aiwaves-cn/agents)] - - -#### Plan reflection - -- [2023/08] **SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning.** *Ning Miao (University of Oxford) et al. arXiv.* [[paper](https://arxiv.org/abs/2308.00436)] [[code](https://github.com/NingMiao/SelfCheck)] -- [2023/05] **ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models.** *Zhipeng Chen (Renmin University of China) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.14323)] [[code](https://github.com/RUCAIBOX/ChatCoT)] -- [2023/05] **Voyager: An Open-Ended Embodied Agent with Large Language Models.** *Guanzhi Wang (NVIDA) et al. arXiv.* [[paper](https://arxiv.org/abs/2305.16291)] [[code](https://voyager.minedojo.org/)] -- [2023/03] **Chat with the Environment: Interactive Multimodal Perception Using Large Language Models.** *Xufeng Zhao (University Hamburg) et al. arXiv.* [[paper](https://arxiv.org/abs/2303.08268)] [[code](https://matcha-model.github.io/)] -- [2022/12] **LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models.** *Chan Hee Song (The Ohio State University) et al. arXiv.* [[paper](https://arxiv.org/abs/2212.04088)] [[code](https://dki-lab.github.io/LLM-Planner/)] -- [2022/10] **ReAct: Synergizing Reasoning and Acting in Language Models.** *Shunyu Yao ( Princeton University) et al. arXiv.* [[paper](https://arxiv.org/abs/2210.03629)] [[code](https://react-lm.github.io/)] -- [2022/07] **Inner Monologue: Embodied Reasoning through Planning with Language Models.** *Wenlong Huang (Robotics at Google) et al. arXiv.* [[paper](https://arxiv.org/abs/2207.05608)] [[code](https://innermonologue.github.io/)] -- [2021/10] **AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts.** *Tongshuang Wu (University of Washington) et al. arXiv.* [[paper](https://arxiv.org/abs/2110.01691)] - -## Appendix -- Example Planning Loop Implementations -- Glossary of Planning Loop Terms From b77450fc3e1b9029951e4be00f45a8014f81c558 Mon Sep 17 00:00:00 2001 From: Nilllas <48855850+Nilllas@users.noreply.github.com> Date: Fri, 20 Oct 2023 15:59:10 +0200 Subject: [PATCH 09/25] testAgent entering the arena (#5845) --- arena/testAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/testAgent.json diff --git a/arena/testAgent.json b/arena/testAgent.json new file mode 100644 index 00000000..02c5b1b8 --- /dev/null +++ b/arena/testAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/Nilllas/AutoGPT", + "timestamp": "2023-10-20T11:27:15.343842", + "commit_hash_to_benchmark": "2187f66149ffa4bb99f9ca6a11b592fe4d683791", + "branch_to_benchmark": "master" +} \ No newline at end of file From 6cee22585e0d6e888703ddd0cfa7a28d71f95a02 Mon Sep 17 00:00:00 2001 From: xpineda Date: Fri, 20 Oct 2023 15:59:46 +0200 Subject: [PATCH 10/25] Pumu2_agent entering the arena (#5844) --- arena/Pumu2_agent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/Pumu2_agent.json diff --git a/arena/Pumu2_agent.json b/arena/Pumu2_agent.json new file mode 100644 index 00000000..52510f0b --- /dev/null +++ b/arena/Pumu2_agent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/xpineda/AutoGPT_xabyvng.git", + "timestamp": "2023-10-20T09:26:07.885410", + "commit_hash_to_benchmark": "2187f66149ffa4bb99f9ca6a11b592fe4d683791", + "branch_to_benchmark": "master" +} \ No newline at end of file From baafadac6976159cfb4e91fbb7671bbec40b327b Mon Sep 17 00:00:00 2001 From: LinYushen Date: Fri, 20 Oct 2023 08:59:59 -0500 Subject: [PATCH 11/25] hello entering the arena (#5843) --- arena/hello.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/hello.json diff --git a/arena/hello.json b/arena/hello.json new file mode 100644 index 00000000..44d8836c --- /dev/null +++ b/arena/hello.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/ldnvnbl/AutoGPT", + "timestamp": "2023-10-20T09:37:16.860422", + "commit_hash_to_benchmark": "2187f66149ffa4bb99f9ca6a11b592fe4d683791", + "branch_to_benchmark": "master" +} \ No newline at end of file From 3dc73e67ab1df66d0300d89db6397f6f652e3bd4 Mon Sep 17 00:00:00 2001 From: xpineda Date: Fri, 20 Oct 2023 16:00:21 +0200 Subject: [PATCH 12/25] Bagi_agent entering the arena (#5842) --- arena/Bagi_agent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/Bagi_agent.json diff --git a/arena/Bagi_agent.json b/arena/Bagi_agent.json new file mode 100644 index 00000000..4251bb42 --- /dev/null +++ b/arena/Bagi_agent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/xpineda/AutoGPT_xabyvng.git", + "timestamp": "2023-10-20T09:21:48.837635", + "commit_hash_to_benchmark": "2187f66149ffa4bb99f9ca6a11b592fe4d683791", + "branch_to_benchmark": "master" +} \ No newline at end of file From 9cabd16bc9506d8d8eedd824fe0f64d6d3690a5b Mon Sep 17 00:00:00 2001 From: albags Date: Fri, 20 Oct 2023 15:01:28 +0100 Subject: [PATCH 13/25] agsCehAgent entering the arena (#5827) --- arena/agsCehAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/agsCehAgent.json diff --git a/arena/agsCehAgent.json b/arena/agsCehAgent.json new file mode 100644 index 00000000..e628e79a --- /dev/null +++ b/arena/agsCehAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/albags/AutoGPT.git", + "timestamp": "2023-10-19T11:30:12.759675", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From 4acc2f5e151338ea8f1a14e8f962862fb7b40097 Mon Sep 17 00:00:00 2001 From: "magic.chen" <28854175+w6m6@users.noreply.github.com> Date: Fri, 20 Oct 2023 22:01:50 +0800 Subject: [PATCH 14/25] devagent entering the arena (#5841) --- arena/devagent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/devagent.json diff --git a/arena/devagent.json b/arena/devagent.json new file mode 100644 index 00000000..f65809e1 --- /dev/null +++ b/arena/devagent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/w6m6/kkgpt", + "timestamp": "2023-10-20T08:29:25.708364", + "commit_hash_to_benchmark": "052802ff8d9354f23620eb8b6a5fd68cda7e5c0e", + "branch_to_benchmark": "master" +} \ No newline at end of file From 6b5cef218f222ec80d8e779fef2f57405186d135 Mon Sep 17 00:00:00 2001 From: Andy Wong Date: Fri, 20 Oct 2023 22:02:06 +0800 Subject: [PATCH 15/25] WYC entering the arena (#5839) --- arena/WYC.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/WYC.json diff --git a/arena/WYC.json b/arena/WYC.json new file mode 100644 index 00000000..0620b0aa --- /dev/null +++ b/arena/WYC.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/131250208/AutoGPT_YC", + "timestamp": "2023-10-20T07:42:11.493899", + "commit_hash_to_benchmark": "9219bfba0e028a557109b8e39c0fd91c1df243f8", + "branch_to_benchmark": "master" +} \ No newline at end of file From fc8622689dc3cd460970a0f2bcad1659c77ef024 Mon Sep 17 00:00:00 2001 From: Umar-Azam <92691687+Umar-Azam@users.noreply.github.com> Date: Fri, 20 Oct 2023 10:02:20 -0400 Subject: [PATCH 16/25] ResearchAgent entering the arena (#5837) --- arena/ResearchAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/ResearchAgent.json diff --git a/arena/ResearchAgent.json b/arena/ResearchAgent.json new file mode 100644 index 00000000..c04a6b57 --- /dev/null +++ b/arena/ResearchAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/Umar-Azam/AutoGPT-ResearchAgent", + "timestamp": "2023-10-20T06:08:12.933685", + "commit_hash_to_benchmark": "9219bfba0e028a557109b8e39c0fd91c1df243f8", + "branch_to_benchmark": "master" +} \ No newline at end of file From b4dd0c6d94b66f2f2fba544a90a0a39662c67789 Mon Sep 17 00:00:00 2001 From: ugyuji Date: Fri, 20 Oct 2023 23:02:34 +0900 Subject: [PATCH 17/25] UGYUJI entering the arena (#5835) --- arena/UGYUJI.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/UGYUJI.json diff --git a/arena/UGYUJI.json b/arena/UGYUJI.json new file mode 100644 index 00000000..2d0abc30 --- /dev/null +++ b/arena/UGYUJI.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/ugyuji/AutoGPT", + "timestamp": "2023-10-20T04:42:28.397067", + "commit_hash_to_benchmark": "052802ff8d9354f23620eb8b6a5fd68cda7e5c0e", + "branch_to_benchmark": "master" +} \ No newline at end of file From 3ffef50dfcae94d2850e128e864d4729ab0f92c0 Mon Sep 17 00:00:00 2001 From: Jay Zhang <42362818+jiezhangGt@users.noreply.github.com> Date: Fri, 20 Oct 2023 22:02:48 +0800 Subject: [PATCH 18/25] ZJgpt entering the arena (#5834) --- arena/ZJgpt.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/ZJgpt.json diff --git a/arena/ZJgpt.json b/arena/ZJgpt.json new file mode 100644 index 00000000..0ac3d256 --- /dev/null +++ b/arena/ZJgpt.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/jiezhangGt/AutoGPT", + "timestamp": "2023-10-20T04:04:28.198603", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From d14f27ac7dbdc2e32d21201028d243674441be4e Mon Sep 17 00:00:00 2001 From: Jay Zhang <42362818+jiezhangGt@users.noreply.github.com> Date: Fri, 20 Oct 2023 22:03:16 +0800 Subject: [PATCH 19/25] YoudaoAutoGPT entering the arena (#5833) --- arena/YoudaoAutoGPT.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/YoudaoAutoGPT.json diff --git a/arena/YoudaoAutoGPT.json b/arena/YoudaoAutoGPT.json new file mode 100644 index 00000000..8e81970e --- /dev/null +++ b/arena/YoudaoAutoGPT.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/jiezhangGt/AutoGPT", + "timestamp": "2023-10-20T03:02:17.342168", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From de2473d0764d561972332476150ccdb57f9d8d93 Mon Sep 17 00:00:00 2001 From: Luis <57528712+LuisLechugaRuiz@users.noreply.github.com> Date: Fri, 20 Oct 2023 16:03:30 +0200 Subject: [PATCH 20/25] AwareAgent entering the arena (#5832) --- arena/AwareAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/AwareAgent.json diff --git a/arena/AwareAgent.json b/arena/AwareAgent.json new file mode 100644 index 00000000..fe7f4487 --- /dev/null +++ b/arena/AwareAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/LuisLechugaRuiz/AwareAgent", + "timestamp": "2023-10-17T14:10:03.198917", + "commit_hash_to_benchmark": "1eadc64dc0a693c7c9de77ddaef857f3a36f7950", + "branch_to_benchmark": "master" +} \ No newline at end of file From 62a9510d611117181577319ce1ff06d5a835d140 Mon Sep 17 00:00:00 2001 From: gabenitez Date: Fri, 20 Oct 2023 11:03:44 -0300 Subject: [PATCH 21/25] MyExample entering the arena (#5831) --- arena/MyExample.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/MyExample.json diff --git a/arena/MyExample.json b/arena/MyExample.json new file mode 100644 index 00000000..508515ae --- /dev/null +++ b/arena/MyExample.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/gabenitez/AutoGPT", + "timestamp": "2023-10-19T22:00:47.453159", + "commit_hash_to_benchmark": "b4588f6425912316e1512391e4392ca30d61e144", + "branch_to_benchmark": "master" +} \ No newline at end of file From c38809a71a10062fcd7ced8b8d0cee362641c515 Mon Sep 17 00:00:00 2001 From: Brad Anderson <2575489+banderson12@users.noreply.github.com> Date: Fri, 20 Oct 2023 10:04:02 -0400 Subject: [PATCH 22/25] contentstrategy entering the arena (#5830) --- arena/contentstrategy.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/contentstrategy.json diff --git a/arena/contentstrategy.json b/arena/contentstrategy.json new file mode 100644 index 00000000..89143267 --- /dev/null +++ b/arena/contentstrategy.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/banderson12/AutoGPT", + "timestamp": "2023-10-19T20:13:23.530323", + "commit_hash_to_benchmark": "b4588f6425912316e1512391e4392ca30d61e144", + "branch_to_benchmark": "master" +} \ No newline at end of file From eab4275cd727c5f5e9d4642fb7e0ed2b14cc691a Mon Sep 17 00:00:00 2001 From: Jovan Kanevche Date: Fri, 20 Oct 2023 16:04:20 +0200 Subject: [PATCH 23/25] UniAgent entering the arena (#5828) --- arena/UniAgent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/UniAgent.json diff --git a/arena/UniAgent.json b/arena/UniAgent.json new file mode 100644 index 00000000..19d710fa --- /dev/null +++ b/arena/UniAgent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/JovanKanevche/AutoGPT", + "timestamp": "2023-10-19T17:04:49.626683", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From fc22dd01c96522409a33aff97a4307beaea0575b Mon Sep 17 00:00:00 2001 From: emads7 <148078635+emads7@users.noreply.github.com> Date: Fri, 20 Oct 2023 17:04:35 +0300 Subject: [PATCH 24/25] LAWYER_EMAD entering the arena (#5826) --- arena/LAWYER_EMAD.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/LAWYER_EMAD.json diff --git a/arena/LAWYER_EMAD.json b/arena/LAWYER_EMAD.json new file mode 100644 index 00000000..5d84d087 --- /dev/null +++ b/arena/LAWYER_EMAD.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/emads7/AutoGPT.git", + "timestamp": "2023-10-19T15:06:37.481038", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file From ef52c2f73a55b00527090202e433cb4a692baa3e Mon Sep 17 00:00:00 2001 From: FIresInWind <148468497+FIresInWind@users.noreply.github.com> Date: Fri, 20 Oct 2023 22:04:49 +0800 Subject: [PATCH 25/25] woohoo_agent entering the arena (#5825) --- arena/woohoo_agent.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 arena/woohoo_agent.json diff --git a/arena/woohoo_agent.json b/arena/woohoo_agent.json new file mode 100644 index 00000000..a805c349 --- /dev/null +++ b/arena/woohoo_agent.json @@ -0,0 +1,6 @@ +{ + "github_repo_url": "https://github.com/FIresInWind/AutoGPT", + "timestamp": "2023-10-19T15:14:59.786203", + "commit_hash_to_benchmark": "4b1e8f6e8b4186ec6563301c146fbf3425f92715", + "branch_to_benchmark": "master" +} \ No newline at end of file