LLM Agent Paper List
A curated paper list on LLM-based agents, derived from an 86-page SCIS cover survey.
The repository contains only a paper list and links, with no code or executable content, so there is no evidence for least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. All trust criteria scored 0.
The repository is a static list with no self-consistency, dependency availability, or failure messages. All reliability criteria scored 0.
The repository targets researchers but does not specify audience scenarios, capability boundaries, trigger precision, or environment fit. All adaptability criteria scored 0.
The repository has a clear table of contents, but lacks installation notes, naming stability, examples and FAQ, known limitations, license, versioning/changelog, and maintenance responsibility. All convention criteria scored 0.
The repository provides a paper list, but output is only links without summaries or usage instructions, marginal value is limited, and cost-benefit is unclear. All effectiveness criteria scored 0.
The paper list provides links but does not separate facts from inferences or provide cross-source corroboration. All verifiability criteria scored 0.
- This repository is only a paper list, not a runnable Agent product; assessment is based on static review with low confidence.
- License information is missing; verify copyright before use.
- Some paper links may be broken; verify them.
What does this agent do, and when should you use it?
This repository maintains a systematic paper list on large language model (LLM) based agents, sourced from the 86-page SCIS cover paper 'The Rise and Potential of Large Language Model Based Agents: A Survey'. The list is organized according to the survey's structure, covering agent construction (brain, perception, action), applications (single-agent, multi-agent, human-agent cooperation), agent societies, and other topics (benchmarks, training). Each entry includes title, authors, year, and links. The repository also features news about related projects such as AgentGym and its reinforcement learning extension AgentGym-RL. The list is maintained by the survey authors and welcomes contributions via PRs or issues.
The repository is a collection of paper entries, each with title, authors, year, links, and occasionally a one-sentence summary. It is organized by topic and subtopic, enabling browsing by area. The README includes news updates pointing to related project websites, HuggingFace datasets, and code repositories. The list also provides links to projects by the same authors, such as AgentGym, AgentGym-RL, and R3. Overall, it serves as a curated resource index, not a runnable software.
- Researchers quickly locate relevant papers on agent construction, applications, and social simulation.
- Students systematically study the LLM agent field using the categorized structure.
- Engineers find papers on specific use cases (e.g., tool use, embodied action) for technical reference.
- Technical writers gather references on topics like surveys, benchmarks, and training methods.
- Researchers following specific projects like AgentGym can track the latest news and linked resources.
What are this agent's strengths and limitations?
- Comprehensive and systematic, covering agent construction, applications, and social simulation.
- Entries include clickable links for easy access to original papers.
- Based on an authoritative SCIS survey paper, ensuring credibility.
- Continuously updated with recent research and project news.
- Provides links to related projects (e.g., AgentGym) for deeper learning.
- Provides only a paper list, without code implementations or runnable demos.
- Paper summaries are brief and some entries lack them; requires reading originals.
- No explicit update frequency or selection criteria for papers.
- Maintenance depends on the authors, risking inconsistent updates.
How do you install or deploy this agent?
No special tools are required to install this directory. Simply clone the repository: git clone https://github.com/WooooDyy/LLM-Agent-Paper-List. Ensure Git is installed.
How do you use this agent?
After cloning, open the README.md file. Use the table of contents to navigate to topics of interest (e.g., '1.1.4 Reasoning & Planning'). Click paper links in the list to read the full text. For entries with code links, visit the respective code repositories. To contribute a new paper, submit a pull request (PR) with the new paper's information.