Difference between revisions of "AI Agents"

From GISAXS
Jump to: navigation, search
(→‎Software Development Workflows)
(→‎Multi-agent)
(27 intermediate revisions by the same user not shown)
Line 11: Line 11:
 
* [https://github.com/open-thought/system-2-research OpenThought - System 2 Research Links]
 
* [https://github.com/open-thought/system-2-research OpenThought - System 2 Research Links]
 
* [https://github.com/hijkzzz/Awesome-LLM-Strawberry Awesome LLM Strawberry (OpenAI o1): Collection of research papers & blogs for OpenAI Strawberry(o1) and Reasoning]
 
* [https://github.com/hijkzzz/Awesome-LLM-Strawberry Awesome LLM Strawberry (OpenAI o1): Collection of research papers & blogs for OpenAI Strawberry(o1) and Reasoning]
 +
* [https://github.com/e2b-dev/awesome-ai-agents Awesome AI Agents]
  
 
===Analysis/Opinions===
 
===Analysis/Opinions===
Line 46: Line 47:
 
* See also: [[Human_Computer_Interaction#AI_Computer_Use]]
 
* See also: [[Human_Computer_Interaction#AI_Computer_Use]]
 
* [https://tavily.com/ Tavily]: Connect Your LLM to the Web: Empowering your AI applications with real-time, accurate search results tailored for LLMs and RAG
 
* [https://tavily.com/ Tavily]: Connect Your LLM to the Web: Empowering your AI applications with real-time, accurate search results tailored for LLMs and RAG
−
* Anthropic [https://www.anthropic.com/news/model-context-protocol Model Context Protocol] (MCP)
+
===Model Context Protocol (MCP)===
 +
* '''Standards:'''
 +
*# Anthropic [https://www.anthropic.com/news/model-context-protocol Model Context Protocol] (MCP)
 +
*# [https://openai.github.io/openai-agents-python/mcp/ OpenAI Agents SDK]
 +
* '''Tools:'''
 
** [https://github.com/jlowin/fastmcp FastMCP]: The fast, Pythonic way to build MCP servers
 
** [https://github.com/jlowin/fastmcp FastMCP]: The fast, Pythonic way to build MCP servers
 +
** [https://github.com/fleuristes/fleur/ Fleur]: A desktop app marketplace for Claude Desktop
 +
* '''Servers:'''
 +
** '''Lists:'''
 +
**# [https://github.com/modelcontextprotocol/servers Model Context Protocol servers]
 +
**# [https://www.mcpt.com/ MCP Servers, One Managed Registry]
 +
** '''Noteworthy:'''
 +
**# [https://github.com/modelcontextprotocol/servers/tree/main/src/github Github MCP server]
 +
**# [https://github.com/modelcontextprotocol/servers/tree/main/src/puppeteer Puppeteer]
 +
**# [https://github.com/modelcontextprotocol/servers/tree/main/src/google-maps Google Maps MCP Server]
 +
**# [https://github.com/modelcontextprotocol/servers/tree/main/src/slack Slack MCP Server]
  
 
===Open-source===
 
===Open-source===
Line 73: Line 88:
 
===Science Agents===
 
===Science Agents===
 
See [[Science Agents]].
 
See [[Science Agents]].
 +
 +
===Medicine===
 +
* 2025-03: [https://news.microsoft.com/2025/03/03/microsoft-dragon-copilot-provides-the-healthcare-industrys-first-unified-voice-ai-assistant-that-enables-clinicians-to-streamline-clinical-documentation-surface-information-and-automate-task/ Microsoft Dragon Copilot]: streamline clinical workflows and paperwork
  
 
===LLM-as-judge===
 
===LLM-as-judge===
Line 83: Line 101:
 
* 2024-11: [https://arxiv.org/abs/2411.15594 A Survey on LLM-as-a-Judge]
 
* 2024-11: [https://arxiv.org/abs/2411.15594 A Survey on LLM-as-a-Judge]
 
* 2024-12: [https://arxiv.org/abs/2412.05579 LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods]
 
* 2024-12: [https://arxiv.org/abs/2412.05579 LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods]
 +
* 2025-03: [https://arxiv.org/abs/2503.19877 Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators]
  
 
===Deep Research===
 
===Deep Research===
Line 96: Line 115:
 
* [https://huggingface.co/ huggingface] [https://huggingface.co/blog/open-deep-research open-Deep-research ([https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research code])
 
* [https://huggingface.co/ huggingface] [https://huggingface.co/blog/open-deep-research open-Deep-research ([https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research code])
 
* xAI Grok 3 Deep Search
 
* xAI Grok 3 Deep Search
 +
* Exa AI [https://exa.ai/websets Websets]
 +
* [https://liner.com/news/introducing-deepresearch Liner Deep Research]
  
 
=Advanced Workflows=
 
=Advanced Workflows=
Line 125: Line 146:
 
## [https://codeium.com/ Codeium] [https://codeium.com/windsurf Windsurf] (with "Cascade" AI Agent)
 
## [https://codeium.com/ Codeium] [https://codeium.com/windsurf Windsurf] (with "Cascade" AI Agent)
 
## ByteDance [https://www.trae.ai/ Trae AI]
 
## ByteDance [https://www.trae.ai/ Trae AI]
 +
## [https://www.tabnine.com/ Tabnine]
 +
## [https://marketplace.visualstudio.com/items?itemName=Traycer.traycer-vscode Traycer]
 +
## [https://idx.dev/ IDX]: free
 
## [https://github.com/codestoryai/aide Aide]: open-source AI-native code editor (fork of VS Code)
 
## [https://github.com/codestoryai/aide Aide]: open-source AI-native code editor (fork of VS Code)
 
## [https://www.continue.dev/ continue.dev]: open-source code assistant
 
## [https://www.continue.dev/ continue.dev]: open-source code assistant
 
## [https://trypear.ai/ Pear AI]: open-source code editor
 
## [https://trypear.ai/ Pear AI]: open-source code editor
 +
## [https://haystackeditor.com/ Haystack Editor]: canvas UI
 +
## [https://onlook.com/ Onlook]: for designers
 
# AI-assisted IDE, where the AI generates and manages the dev environment
 
# AI-assisted IDE, where the AI generates and manages the dev environment
 
## [https://replit.com/ Replit]
 
## [https://replit.com/ Replit]
Line 147: Line 173:
 
## [https://databutton.com/ Databutton]: no-code software development
 
## [https://databutton.com/ Databutton]: no-code software development
 
## [https://base44.com/ base44]: no-code dashboard apps
 
## [https://base44.com/ base44]: no-code dashboard apps
 +
## [https://www.theorigin.ai/ Origin AI]
 
# Semi-autonomous software engineer agents
 
# Semi-autonomous software engineer agents
 
## [https://www.cognition.ai/blog/introducing-devin Devin] (Cognition AI)
 
## [https://www.cognition.ai/blog/introducing-devin Devin] (Cognition AI)
−
## [https://aws.amazon.com/q/ Amazon Q]
+
## [https://aws.amazon.com/q/ Amazon Q] (and CodeWhisperer)
 
## [https://honeycomb.sh/ Honeycomb]
 
## [https://honeycomb.sh/ Honeycomb]
 
## [https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview Claude Code]
 
## [https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview Claude Code]
Line 168: Line 195:
 
==Inference-compute Reasoning==
 
==Inference-compute Reasoning==
 
* [https://nousresearch.com/#popup-menu-anchor Nous Research]: [https://nousresearch.com/introducing-the-forge-reasoning-api-beta-and-nous-chat-an-evolution-in-llm-inference/ Forge Reasoning API Beta]
 
* [https://nousresearch.com/#popup-menu-anchor Nous Research]: [https://nousresearch.com/introducing-the-forge-reasoning-api-beta-and-nous-chat-an-evolution-in-llm-inference/ Forge Reasoning API Beta]
 +
 +
==AI Assistant==
 +
* [https://convergence.ai/ Convergence] [https://proxy.convergence.ai/ Proxy]
  
 
==Agentic Systems==
 
==Agentic Systems==
Line 173: Line 203:
 
* [https://www.cognition.ai/ Cognition AI]: [https://www.cognition.ai/blog/introducing-devin Devin] software engineer (14% SWE-Agent)
 
* [https://www.cognition.ai/ Cognition AI]: [https://www.cognition.ai/blog/introducing-devin Devin] software engineer (14% SWE-Agent)
 
* [https://honeycomb.sh/ Honeycomb] ([https://honeycomb.sh/blog/swe-bench-technical-report 22% SWE-Agent])
 
* [https://honeycomb.sh/ Honeycomb] ([https://honeycomb.sh/blog/swe-bench-technical-report 22% SWE-Agent])
 +
* [https://www.factory.ai/ Factory AI]
  
 
=Increasing AI Agent Intelligence=
 
=Increasing AI Agent Intelligence=
Line 179: Line 210:
 
=Multi-agent orchestration=
 
=Multi-agent orchestration=
 
==Research==
 
==Research==
 +
* 2025-03: [https://arxiv.org/abs/2503.13657 Why Do Multi-Agent LLM Systems Fail?]
 +
* 2025-03: [https://arxiv.org/abs/2503.15478 SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks]
 +
 +
===Organization Schemes===
 +
* 2025-03: [https://arxiv.org/abs/2503.02390 ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks]
 +
 
===Societies and Communities of AI agents===
 
===Societies and Communities of AI agents===
 
* 2024-12: [https://arxiv.org/abs/2412.10270 Cultural Evolution of Cooperation among LLM Agents]
 
* 2024-12: [https://arxiv.org/abs/2412.10270 Cultural Evolution of Cooperation among LLM Agents]
Line 207: Line 244:
 
* 2024-10: [https://arxiv.org/abs/2410.08164 Agent S: An Open Agentic Framework that Uses Computers Like a Human] ([https://github.com/simular-ai/Agent-S code])
 
* 2024-10: [https://arxiv.org/abs/2410.08164 Agent S: An Open Agentic Framework that Uses Computers Like a Human] ([https://github.com/simular-ai/Agent-S code])
 
* 2024-10: [https://arxiv.org/abs/2410.20424 AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions]
 
* 2024-10: [https://arxiv.org/abs/2410.20424 AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions]
 +
* 2025-02: [https://arxiv.org/abs/2502.16111 PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving]
  
 
===Related work===
 
===Related work===
Line 233: Line 271:
 
* [https://github.com/HKUDS/AutoAgent AutoAgent]: Fully-Automated & Zero-Code LLM Agent Framework
 
* [https://github.com/HKUDS/AutoAgent AutoAgent]: Fully-Automated & Zero-Code LLM Agent Framework
 
* [https://mastra.ai/ Mastra] ([https://github.com/mastra-ai/mastra github]): opinionated Typescript framework for AI applications (primitives for workflows, agents, RAG, integrations and evals)
 
* [https://mastra.ai/ Mastra] ([https://github.com/mastra-ai/mastra github]): opinionated Typescript framework for AI applications (primitives for workflows, agents, RAG, integrations and evals)
 +
* [https://github.com/orra-dev/orra Orra]: multi-agent applications with complex real-world interactions
 +
* [https://github.com/gensx-inc/gensx/blob/main/README.md GenSX]
 +
* Cloudflare [https://developers.cloudflare.com/agents/ agents-sdk] ([https://blog.cloudflare.com/build-ai-agents-on-cloudflare/ info], [https://github.com/cloudflare/agents code])
 +
* OpenAI [https://platform.openai.com/docs/api-reference/responses responses API] and [https://platform.openai.com/docs/guides/agents agents SDK]
  
 
==Open Source Systems==
 
==Open Source Systems==
Line 262: Line 304:
 
* [https://ottogrid.ai/ Otto Grid]
 
* [https://ottogrid.ai/ Otto Grid]
 
* [https://www.paradigmai.com/ Paradigm]
 
* [https://www.paradigmai.com/ Paradigm]
 +
* [https://www.superworker.ai/ Superworker AI]
  
 
==Cloud solutions==
 
==Cloud solutions==
Line 277: Line 320:
  
 
=Optimization=
 
=Optimization=
 +
===Reviews===
 +
* 2024-12: [https://arxiv.org/abs/2412.11936 A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges]
 +
* 2025-03: [https://arxiv.org/abs/2503.16416 Survey on Evaluation of LLM-based Agents]
 +
 
===Metrics, Benchmarks===
 
===Metrics, Benchmarks===
 
* 2019-11: [https://arxiv.org/abs/1911.01547 On the Measure of Intelligence]
 
* 2019-11: [https://arxiv.org/abs/1911.01547 On the Measure of Intelligence]
Line 296: Line 343:
 
* 2024-11: [https://arxiv.org/abs/2411.13543 BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games]
 
* 2024-11: [https://arxiv.org/abs/2411.13543 BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games]
 
* 2024-12: [https://arxiv.org/abs/2412.14161 TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks] ([https://github.com/TheAgentCompany/TheAgentCompany code], [https://the-agent-company.com/ project], [https://the-agent-company.com/#/leaderboard leaderboard])
 
* 2024-12: [https://arxiv.org/abs/2412.14161 TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks] ([https://github.com/TheAgentCompany/TheAgentCompany code], [https://the-agent-company.com/ project], [https://the-agent-company.com/#/leaderboard leaderboard])
−
* 2024-12: [https://arxiv.org/abs/2412.11936 A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges]
 
 
* 2025-01: [https://codeelo-bench.github.io/ CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings] ([https://arxiv.org/abs/2501.01257 preprint], [https://codeelo-bench.github.io/#leaderboard-table leaderboard])
 
* 2025-01: [https://codeelo-bench.github.io/ CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings] ([https://arxiv.org/abs/2501.01257 preprint], [https://codeelo-bench.github.io/#leaderboard-table leaderboard])
 
* 2025-02: [https://static.scale.com/uploads/654197dc94d34f66c0f5184e/EnigmaEval%20v4.pdf ENIGMAEVAL:A Benchmark of Long Multimodal Reasoning Challenges] ([https://scale.com/leaderboard/enigma_eval leaderboard])
 
* 2025-02: [https://static.scale.com/uploads/654197dc94d34f66c0f5184e/EnigmaEval%20v4.pdf ENIGMAEVAL:A Benchmark of Long Multimodal Reasoning Challenges] ([https://scale.com/leaderboard/enigma_eval leaderboard])
 
* 2025-02: [https://sites.google.com/view/mlgym MLGym: A New Framework and Benchmark for Advancing AI Research Agents] ([https://arxiv.org/abs/2502.14499 paper], [https://github.com/facebookresearch/MLGym code])
 
* 2025-02: [https://sites.google.com/view/mlgym MLGym: A New Framework and Benchmark for Advancing AI Research Agents] ([https://arxiv.org/abs/2502.14499 paper], [https://github.com/facebookresearch/MLGym code])
 +
* 2025-02: [https://arxiv.org/abs/2502.18356 WebGames: Challenging General-Purpose Web-Browsing AI Agents]
 +
* 2025-03: ColBench: [https://arxiv.org/abs/2503.15478 SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks]
  
 
===Evaluation Schemes===
 
===Evaluation Schemes===
Line 307: Line 355:
 
===Multi-agent===
 
===Multi-agent===
 
* 2024-12: [https://arxiv.org/abs/2412.10270 Cultural Evolution of Cooperation among LLM Agents]
 
* 2024-12: [https://arxiv.org/abs/2412.10270 Cultural Evolution of Cooperation among LLM Agents]
 +
* [https://github.com/lechmazur/step_game/ Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure]
  
 
===Agent Challenges===
 
===Agent Challenges===
Line 322: Line 371:
 
=See Also=
 
=See Also=
 
* [[Science Agents]]
 
* [[Science Agents]]
 +
* [[Increasing AI Intelligence]]
 
* [[AI tools]]
 
* [[AI tools]]
 
* [[AI understanding]]
 
* [[AI understanding]]
 
* [[Robots]]
 
* [[Robots]]
 
* [[Exocortex]]
 
* [[Exocortex]]

Revision as of 13:51, 27 March 2025

Reviews & Perspectives

Published

Continually updating

Analysis/Opinions

Guides

AI Assistants

Components of AI Assistants

Agent Internal Workflow Management

Information Retrieval (Memory)

Contextual Memory

  • Memobase: user profile-based memory (long-term user memory for genAI) applications)

Control (tool-use, computer use, etc.)

Model Context Protocol (MCP)

Open-source

Personalities/Personas

Specific Uses for AI Assistants

Computer Use

Software Engineering

Science Agents

See Science Agents.

Medicine

LLM-as-judge

Deep Research

Advanced Workflows

Streamline Administrative Tasks

Author Research Articles

Software Development Workflows

Several paradigms of AI-assisted coding have arisen:

  1. Manual, human driven
  2. AI-aided through chat/dialogue, where the human asks for code and then copies it into the project
    1. OpenAI ChatGPT
    2. Anthropic Claude
  3. API calls to an LLM, which generates code and inserts the file into the project
  4. LLM-integration into the IDE
    1. Copilot
    2. Qodo (Codium) & AlphaCodium (preprint, code)
    3. Cursor
    4. Codeium Windsurf (with "Cascade" AI Agent)
    5. ByteDance Trae AI
    6. Tabnine
    7. Traycer
    8. IDX: free
    9. Aide: open-source AI-native code editor (fork of VS Code)
    10. continue.dev: open-source code assistant
    11. Pear AI: open-source code editor
    12. Haystack Editor: canvas UI
    13. Onlook: for designers
  5. AI-assisted IDE, where the AI generates and manages the dev environment
    1. Replit
    2. Aider (code): Pair programming on commandline
    3. Pythagora
    4. StackBlitz bolt.new
    5. Cline (formerly Claude Dev)
  6. Prompt-to-product
    1. Github Spark (demo video)
    2. Create.xyz: text-to-app, replicate product from link
    3. a0.dev: generate mobil apps (from your phone)
    4. Softgen: web app developer
    5. wrapifai: build form-based apps
    6. Lovable: web app (from text, screenshot, etc.)
    7. Vercel v0
    8. MarsX (John Rush): SaaS builder
    9. Webdraw: turn sketches into web apps
    10. Tempo Labs: build React apps
    11. Databutton: no-code software development
    12. base44: no-code dashboard apps
    13. Origin AI
  7. Semi-autonomous software engineer agents
    1. Devin (Cognition AI)
    2. Amazon Q (and CodeWhisperer)
    3. Honeycomb
    4. Claude Code

For a review of the current state of software-engineering agentic approaches, see:

Corporate AI Agent Ventures

Mundane Workflows and Capabilities

Inference-compute Reasoning

AI Assistant

Agentic Systems

Increasing AI Agent Intelligence

See: Increasing AI Intelligence

Multi-agent orchestration

Research

Organization Schemes

Societies and Communities of AI agents

Domain-specific

Research demos

Related work

Inter-agent communications

Architectures

Open Source Frameworks

Open Source Systems

Commercial Automation Frameworks

Spreadsheet

Cloud solutions

Frameworks

Optimization

Reviews

Metrics, Benchmarks

Evaluation Schemes

Multi-agent

Agent Challenges

  • Aidan-Bench: Test creativity by having a particular LLM generate long sequence of outputs (meant to be different), and measuring how long it can go before duplications appear.
  • Pictionary: LLM suggests prompt, multiple LLMs generate outputs, LLM judges; allows raking of the generation abilities.
  • MC-bench: Request LLMs to build an elaborate structure in Minecraft; outputs can be A/B tested by human judges.

Automated Improvement

See Also

Retrieved from "http://gisaxs.com/index.php?title=AI_Agents&oldid=7369"