Autonomous Agents Research Papers
Daily-updated curated list of research papers on autonomous agents (LLMs).
- Source repo
- tmgthb/Autonomous-Agents
- Stars
- ★ 1.4k
- Last updated
- 3mo ago
- License
- MIT
- FA score
- 28/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- Typical use
- Researchers quickly scan the latest papers in autonomous agents.
- Not a fit if
- Researchers who need runnable code or tools
- Users who need search, filtering, or citation features
- Readers who want full paper text rather than links
- Source review
- 28/100 · Major gaps 7 safety controls not found
What does this agent do, and when should you use it?
Autonomous-Agents is a curated collection of research papers on autonomous agents (LLMs), updated daily. The repository organizes papers by year in separate markdown files, allowing chronological browsing. Each entry provides the paper title, arXiv link, and a bullet-point summary of key contributions. It serves as a literature tracking tool for researchers and practitioners to stay current. The repository is MIT licensed and includes a resources section.
The repository maintains a chronologically ordered list of research papers, updated daily. Each paper entry includes title, arXiv link, and summary bullets. Papers are grouped by year and month, linked to separate markdown files under resources/. A resources section provides additional content.
- Researchers quickly scan the latest papers in autonomous agents.
- Practitioners track specific topics like multi-agent systems or embodied agents.
- Students find introductory papers and classic literature.
- Tech enthusiasts get daily summaries of arXiv papers.
How do you install or deploy this agent?
Installation requires Git to clone the repository. Command: git clone https://github.com/tmgthb/Autonomous-Agents.gitHow do you use this agent?
After cloning, open README.md for the latest papers, or browse year-based files in resources/. For example, view resources/Autonomous_Agents_Research_Papers_2026_5.md for May 2026 papers.
What are this agent's strengths and limitations?
- Daily updates ensure freshness
- Papers are organized chronologically for easy browsing
- Each entry includes concise bullet summaries
- Covers diverse areas: multi-agent, embodied, etc.
- Provides only paper lists, not full text or code
- No search or filtering functionality
- Requires manual browsing of multiple files
- No citation format provided (except BibTeX style reference)
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 |
|---|---|---|---|---|---|---|
| Autonomous Agents Research Papers This agent | 28 · Major gaps | Library / SDKFree | ★ 1.4k | 3mo ago | — | — |
| XScientist | 61 · Some gaps | CLIFree + model costs | ★ 125 | 1d ago | Python | OpenAI API · Claude API |
| LLM Agent Paper List | 0 · Major gaps | Library / SDKFree | ★ 8.3k | 1y ago | — | — |
| Luxas Research Colleague | 59 · Major gaps | CLIFree + model costs | ★ 1.2k | 1mo ago | TypeScript | Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
This repository is a list of research papers with no executable code or agent functionality. Therefore, there is no least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, or rollback. Source attribution is partially present: paper entries include arXiv links and author information, but selection criteria or verification process are not stated.
Self-consistency: README structure is clear, paper entries are consistently formatted, and links point to arXiv. Dependency availability: No code or dependencies. Failure messages: No code or runtime behavior.
Audience and scenarios: Aimed at researchers and practitioners interested in autonomous agents, providing a list of papers organized by year. Capability boundaries: Not explicitly stated, but implied as paper aggregation. Trigger precision: Not applicable as there is no automated trigger. Environment fit: Static documentation only, no environment requirements.
Information architecture: README provides clear navigation and categorization. Install notes: Not applicable as there is no code. Naming stability: Repository name and structure are stable. Examples and FAQ: Paper abstracts serve as examples, but no FAQ. Known limitations: Not mentioned. License: MIT license is explicit. Versioning and changelog: Updates by year, but no formal changelog. Maintenance responsibility: Author Teemu Maatta is explicit, but not verified.
Output usability: Paper list and abstracts are easy to browse. Marginal value: Provides daily updated paper aggregation, useful for researchers. Cost benefit: No code, no runtime cost, but maintenance cost unknown.
Claim traceability: Each paper has an arXiv link, traceable. Cross-source corroboration: No other sources provided. Fact-inference separation: Abstracts may contain inferences, but not explicitly separated.
- 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.
- This repository contains no executable code or agent functionality; it is only a list of papers.
- Paper selection criteria and verification process are not stated, so information may be unverified.
- Publisher identity is unverified, and maintenance responsibility is unclear.