LLM Agent Paper List
A curated paper list on LLM-based agents, derived from an 86-page SCIS cover survey.
- Source repo
- WooooDyy/LLM-Agent-Paper-List
- Stars
- ★ 8.3k
- Last updated
- 1y ago
- FA score
- 0/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- Researchers quickly locate relevant papers on agent construction, applications, and social simulation.
- Not a fit if
- Developers who need runnable code or demos
- Readers wanting full paper summaries and selection criteria
- Teams needing a guaranteed update schedule
- Source review
- 0/100 · Major gaps 8 safety controls not found
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.
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.
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 does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| LLM Agent Paper List This agent | 0 · Major gaps | Library / SDKFree | ★ 8.3k | 1y ago | — | — |
| Autonomous Agents Research Papers | 28 · Major gaps | Library / SDKFree | ★ 1.4k | 3mo ago | — | — |
| AgileRL | 71 · Some gaps | Library / SDKFreemium | ★ 959 | today | Python | — |
| XScientist | 61 · Some gaps | CLIFree + model costs | ★ 125 | 1d ago | Python | OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
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.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- 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.