NLP Wiki

User Tools

Site Tools

Trace: • autonomous_language_agents
nlp:autonomous_language_agents

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:autonomous_language_agents [2025/06/02 06:43] – [Papers] jmflanignlp:autonomous_language_agents [2026/03/05 00:02] (current) – [Papers] jmflanig
Line 13: Line 13:
   * **Architectures**   * **Architectures**
     * [[https://arxiv.org/pdf/2309.02427|Sumers et al 2024 - Cognitive Architectures for Language Agents]]     * [[https://arxiv.org/pdf/2309.02427|Sumers et al 2024 - Cognitive Architectures for Language Agents]]
 +  * **Memory Architectures**
 +    * [[https://arxiv.org/pdf/2501.13956|Rasmussen et al 2025 - Zep: A Temporal Knowledge Graph Architecture for Agent Memory]]
   * **Multi-Agents**   * **Multi-Agents**
     * [[https://arxiv.org/pdf/2501.06322|Tran et al 2025 - Multi-Agent Collaboration Mechanisms: A Survey of LLMs]]     * [[https://arxiv.org/pdf/2501.06322|Tran et al 2025 - Multi-Agent Collaboration Mechanisms: A Survey of LLMs]]
 +  * **Applications**
 +    * GUI Agents
 +      * [[https://arxiv.org/pdf/2411.04890|Wang et al 2024 - GUI Agents with Foundation Models: A Comprehensive Survey]]
 +      * [[https://arxiv.org/pdf/2411.18279|Zhang et al 2024 - Large Language Model-Brained GUI Agents: A Survey]]
 +    * Personal Agents
 +      * [[https://arxiv.org/pdf/2401.05459|Li et al 2024 - Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security]]
  
 ===== Papers ===== ===== Papers =====
Line 21: Line 29:
       * Follow-up work: [[https://arxiv.org/pdf/2402.00658|Jiao et al 2024 - Learning Planning-based Reasoning via Trajectories Collection and Process Reward Synthesizing]]       * Follow-up work: [[https://arxiv.org/pdf/2402.00658|Jiao et al 2024 - Learning Planning-based Reasoning via Trajectories Collection and Process Reward Synthesizing]]
     * [[https://arxiv.org/pdf/2303.11366|Shinn et al 2023 - Reflexion: Language Agents with Verbal Reinforcement Learning]]     * [[https://arxiv.org/pdf/2303.11366|Shinn et al 2023 - Reflexion: Language Agents with Verbal Reinforcement Learning]]
 +    * [[https://arxiv.org/pdf/2308.10144|Zhao et al 2023 - ExpeL: LLM Agents Are Experiential Learners]]
     * [[https://arxiv.org/pdf/2310.05915|Chen et al 2023 - FireAct: Toward Language Agent Fine-tuning]] Fine-tunes the LLM agent     * [[https://arxiv.org/pdf/2310.05915|Chen et al 2023 - FireAct: Toward Language Agent Fine-tuning]] Fine-tunes the LLM agent
     * CodeAct: [[https://arxiv.org/pdf/2402.01030|Wang et al 2024 - Executable Code Actions Elicit Better LLM Agents]]     * CodeAct: [[https://arxiv.org/pdf/2402.01030|Wang et al 2024 - Executable Code Actions Elicit Better LLM Agents]]
   * AutoGPT: [[https://arxiv.org/pdf/2306.02224.pdf|Yang et al 2023 - Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions]] [[https://github.com/Significant-Gravitas/AutoGPT|github]]   * AutoGPT: [[https://arxiv.org/pdf/2306.02224.pdf|Yang et al 2023 - Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions]] [[https://github.com/Significant-Gravitas/AutoGPT|github]]
-  * [[https://arxiv.org/pdf/2308.10144|Zhao et al 2023 - ExpeL: LLM Agents Are Experiential Learners]] 
   * [[https://arxiv.org/pdf/2309.07870.pdf|Zhou et al 2023 - Agents: An Open-source Framework for Autonomous Language Agents]]   * [[https://arxiv.org/pdf/2309.07870.pdf|Zhou et al 2023 - Agents: An Open-source Framework for Autonomous Language Agents]]
   * [[https://arxiv.org/pdf/2403.12881|Chen et al 2023 - Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models]]   * [[https://arxiv.org/pdf/2403.12881|Chen et al 2023 - Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models]]
-  * [[https://arxiv.org/pdf/2412.05467|De Chezelles et al 2024 - The BrowserGym Ecosystem for Web Agent Research]] 
   * [[https://arxiv.org/pdf/2502.04644|Wu et al 2025 - Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research]]   * [[https://arxiv.org/pdf/2502.04644|Wu et al 2025 - Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research]]
   * [[https://openai.com/index/introducing-deep-research/|OpenAI 2025 - Deep Research]]   * [[https://openai.com/index/introducing-deep-research/|OpenAI 2025 - Deep Research]]
   * [[https://arxiv.org/pdf/2505.21963|Yano et al 2025 - LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents]]   * [[https://arxiv.org/pdf/2505.21963|Yano et al 2025 - LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents]]
   * [[https://arxiv.org/pdf/2505.22571|Pham et al 2025 - Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems]]   * [[https://arxiv.org/pdf/2505.22571|Pham et al 2025 - Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems]]
 +  * **Tool Use and Agent Skills**
 +    * "Agent Skills are instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently" (from [[https://agentskills.io/home|here]])
 +    * [[https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview|Claude - Agent Skills]] (I believe "agent skills" was introduced in Claude)
 +    * [[https://agentskills.io/home|Agent Skills (website)]]
 +    * [[https://arxiv.org/pdf/2602.12670|Li et al 2026 - SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks]]
   * **Software Engineering (SWE) Agents**   * **Software Engineering (SWE) Agents**
 +    * See also [[Software Engineering]]
 +    * [[https://arxiv.org/pdf/2310.06770|Jimenez et al 2023 - SWE-bench: Can Language Models Resolve Real-World GitHub Issues?]]
 +    * [[https://arxiv.org/pdf/2405.15793|Yang et al 2024 - SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering]]
     * [[https://arxiv.org/pdf/2505.23422|Lindenbauer et al 2025 - From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents]]     * [[https://arxiv.org/pdf/2505.23422|Lindenbauer et al 2025 - From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents]]
 +  * **Web Agents**
 +    * MiniWoB: [[https://proceedings.mlr.press/v70/shi17a/shi17a.pdf|Shi et al 2017 - World of Bits: An Open-Domain Platform for Web-Based Agents]]
 +    * MiniWoB++: [[https://arxiv.org/pdf/1802.08802|Liu et al 2018 - Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration]] [[https://miniwob.farama.org/index.html|MiniWoB++]]
 +    * [[https://arxiv.org/pdf/2307.13854|Zhou et al 2023 - WebArena: A Realistic Web Environment for Building Autonomous Agents]]
 +    * [[https://arxiv.org/pdf/2401.13649|Koh et al 2024 - VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks]]
 +    * [[https://arxiv.org/pdf/2412.05467|De Chezelles et al 2024 - The BrowserGym Ecosystem for Web Agent Research]]
 +  * **Mobile UI Agents**
 +    * [[https://arxiv.org/pdf/2404.05719|You et al 2024 - Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs]]
   * **OS Agents**   * **OS Agents**
     * [[https://arxiv.org/pdf/2402.07456|Wu et al 2024 - OS-Copilot: Towards Generalist Computer Agents with Self-Improvement]]     * [[https://arxiv.org/pdf/2402.07456|Wu et al 2024 - OS-Copilot: Towards Generalist Computer Agents with Self-Improvement]]
 +    * [[https://arxiv.org/pdf/2404.07972|Xie et al 2024 - OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ]]
  
 ===== Multi-Agents ===== ===== Multi-Agents =====
Line 46: Line 69:
  
 ===== Related Pages ===== ===== Related Pages =====
 +  * [[ml:Computer Use Agents]]
   * [[Dialog]]   * [[Dialog]]
   * [[Language Model]]   * [[Language Model]]
   * [[Prompting]]   * [[Prompting]]
nlp/autonomous_language_agents.1748846610.txt.gz · Last modified: 2025/06/02 06:43 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki