--- title: "LLM-Agent-Paper-List vs ReAct" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/woooodyy-llm-agent-paper-list-vs-ysymyth-react" tools: ["woooodyy-llm-agent-paper-list", "ysymyth-react"] --- # LLM-Agent-Paper-List vs ReAct *GraphCanon updated Aug 17, 2026* ## Verdict Pick LLM-Agent-Paper-List if lists essential papers on LLM-based agents with integrated tools like AgentGym for RL training; pick ReAct if reAct enhances large language models by improving reasoning and executing actions through specific tasks using GPT-3. [LLM-Agent-Paper-List](https://arxiv.org/abs/2309.07864) reports 8.2k GitHub stars, 495 forks, and 31 open issues, last pushed Sep 12, 2025. [ReAct](https://github.com/ysymyth/ReAct) has 4.1k stars, 396 forks, and 5 open issues, last pushed Feb 6, 2024. Figures are from public GitHub metadata via [LLM-Agent-Paper-List's repository](https://github.com/WooooDyy/LLM-Agent-Paper-List) and [ReAct's repository](https://github.com/ysymyth/ReAct). | | [LLM-Agent-Paper-List](/tools/woooodyy-llm-agent-paper-list.md) | [ReAct](/tools/ysymyth-react.md) | | --- | --- | --- | | Tagline | Must-read papers for LLM-based agents. | ReAct Prompting for decision-making with language models | | Stars | 8,172 | 4,109 | | Forks | 495 | 396 | | Open issues | 31 | 5 | | Language | - | Jupyter Notebook | | Adopt for | Lists essential papers on LLM-based agents with integrated tools like AgentGym for RL training. | ReAct enhances large language models by improving reasoning and executing actions through specific tasks using GPT-3. | | Persona | - | - | | Runtime | - | - | | License | - | MIT | | Categories | AI Agents, Evaluation & Observability | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [LLM-Agent-Paper-List](/tools/woooodyy-llm-agent-paper-list.md) | [ReAct](/tools/ysymyth-react.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Dormant (18%) | | Days since push | 339d | 923d | | Open issues (now) | 31 | 5 | | Stars delta | +4 (30d) | +50 (30d) | | Open issues delta | +2 (30d) | 0 (30d) | | Full report | [trust report](/tools/woooodyy-llm-agent-paper-list/trust.md) | [trust report](/tools/ysymyth-react/trust.md) | ## Decision facts: LLM-Agent-Paper-List - **Adopt for:** Lists essential papers on LLM-based agents with integrated tools like AgentGym for RL training. ## Decision facts: ReAct - **Adopt for:** ReAct enhances large language models by improving reasoning and executing actions through specific tasks using GPT-3. ## Choose when ### Choose LLM-Agent-Paper-List if… - Tags unique to LLM-Agent-Paper-List: agent, nlp, rl. - Also covers Evaluation & Observability. - Looking to survey key advancements in LLM-based agent research, specifically through papers endorsed by authors. ### Choose ReAct if… - Tags unique to ReAct: decision-making, prompting, reasoning. - Also covers LLM Frameworks. - When aiming for better decision-making in HotpotQA, alfworld environments, or WebShop scenarios with GPT-3 ## When NOT to use LLM-Agent-Paper-List - Seeking real-time interactive debugging tools; focuses more on paper reviews and general frameworks than coding sandbox features. - Require support documentation in languages other than English or project-specific code details, as licensing and detailed documentation are currently unverified. ## When NOT to use ReAct - If requiring extensive custom task integration beyond provided notebooks, LangChain's zero-shot ReAct agent may be more preferable - When PaLM outperforms GPT-3 on specific tasks or if an alternative model is preferred ## Common questions ### What is the difference between LLM-Agent-Paper-List and ReAct? LLM-Agent-Paper-List: Must-read papers for LLM-based agents.. ReAct: ReAct Prompting for decision-making with language models. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLM-Agent-Paper-List over ReAct? Choose LLM-Agent-Paper-List over ReAct when Tags unique to LLM-Agent-Paper-List: agent, nlp, rl; Also covers Evaluation & Observability; Looking to survey key advancements in LLM-based agent research, specifically through papers endorsed by authors. ### When should I choose ReAct over LLM-Agent-Paper-List? Choose ReAct over LLM-Agent-Paper-List when Tags unique to ReAct: decision-making, prompting, reasoning; Also covers LLM Frameworks; When aiming for better decision-making in HotpotQA, alfworld environments, or WebShop scenarios with GPT-3. ### When should I avoid LLM-Agent-Paper-List? Seeking real-time interactive debugging tools; focuses more on paper reviews and general frameworks than coding sandbox features. Require support documentation in languages other than English or project-specific code details, as licensing and detailed documentation are currently unverified. ### When should I avoid ReAct? If requiring extensive custom task integration beyond provided notebooks, LangChain's zero-shot ReAct agent may be more preferable When PaLM outperforms GPT-3 on specific tasks or if an alternative model is preferred ### Is LLM-Agent-Paper-List or ReAct more popular on GitHub? LLM-Agent-Paper-List has more GitHub stars (8,172 vs 4,109). Stars measure visibility, not whether either tool fits your constraints. ### Are LLM-Agent-Paper-List and ReAct open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to LLM-Agent-Paper-List or ReAct? GraphCanon lists graph-backed alternatives at [LLM-Agent-Paper-List alternatives](/tools/woooodyy-llm-agent-paper-list/alternatives) and [ReAct alternatives](/tools/ysymyth-react/alternatives) ([LLM-Agent-Paper-List markdown twin](/tools/woooodyy-llm-agent-paper-list/alternatives.md), [ReAct markdown twin](/tools/ysymyth-react/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/woooodyy-llm-agent-paper-list-vs-ysymyth-react.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, LLM-Agent-Paper-List or ReAct? LLM-Agent-Paper-List: Slowing. ReAct: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for LLM-Agent-Paper-List and ReAct? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLM-Agent-Paper-List trust report](/tools/woooodyy-llm-agent-paper-list/trust); [ReAct trust report](/tools/ysymyth-react/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=woooodyy-llm-agent-paper-list`](/api/graphcanon/graph?tool=woooodyy-llm-agent-paper-list) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_