ReAct: Synergizing Reasoning and Acting in Language Models · HackerPapers discussions

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by elij

Tue, 08 Sep 2026 04:02:32 GMT

he's just talking about going from ReAct [1] to Ratchet [2]. It's largely understood in all tooling (langraph, workflows/goal, honcho, bot mode etc.). [1] https://arxiv.org/abs/2210.03629 [2] https://arxiv.org/abs/2605.22148

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Sun, 15 Feb 2026 06:57:48 GMT

To ReAct or not to ReAct?

Recently I've been learning about [LLM-powered ReAct architecture](https://arxiv.org/pdf/2210.03629) for designing software solutions. I've also worked on a high-scale production implementation of this approach, which got me thinking about all the applications I've built in the past. Theoretically, any of them could be implemented using the ReAct architecture(I encourage you to go through the same though exercise), but I'm still grappling with when this makes sense and when it doesn't. Some applications clearly benefit from LLM-backed reasoning—particularly those with heavy business logic…

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by simonw

Sat, 13 Dec 2025 13:09:07 GMT

I'd credit tool calling to the ReAct paper, which was Princeton CA and Google DeepMind: https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by belter

Sun, 27 Jul 2025 14:22:55 GMT

Is this not a variation of ReAct + Chain-of-Thought + Structured Planning? Or is that too unfair to the authors work? [1] - https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by minimaxir

Mon, 14 Apr 2025 01:12:37 GMT

The LLM is what decides which endpoint/tool to call (or none at all) in response to the user input. The original 2022 ReACT paper is still best explainer: https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Sat, 28 Dec 2024 23:45:41 GMT

ReAct: Synergizing Reasoning and Acting in Language Models

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Thu, 05 Dec 2024 23:00:20 GMT

Show HN: Data Connector – Chat with Your Database and APIs

Hey HN! Wanted to share a project I have been working. Data Connector is an open source tool for interacting with Databases (Postgres, MySQL, SQLite) using natural language. Prompts are handled using a ReAct[1] agent which has access to the schema and a tool for executing queries. It also has experimental[2] support for calling APIs (OpenAPI, GraphQL) which allows for queries that can span multiple systems (Find this user's details in Clerk, etc). We have mostly been using it for managing our local development environment, but it has configurable controls for running in other environments.…

17 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by brianshaler

Wed, 07 Aug 2024 17:07:16 GMT

For anyone like me that wondered if "ReAct webapp" was a weird way of capitalizing the React webapp Javascript framework, it appears to be about a Reasoning and Acting methodology[0] with LLMs. Maybe obvious for anyone with more of a pulse on the latest in the LLM space, but it was new to me and took some digging to get more context. [0] https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Fri, 17 May 2024 21:06:58 GMT

ReAct: Synergizing Reasoning and Acting in Language Models (2022)

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by unoti

Mon, 25 Sep 2023 17:40:48 GMT

I think you're 100% on the right track here. The key is memory, loops, and maybe a few other things like external interfaces which are just plain code and not deep learning voodoo. Many things do indeed run LLM's in a loop and attach external sources. See for example AutoGPT, the ReAct paper[1], and the Reflexion paper[2]. ReAct one line summary: This is about giving the machine tools that are external interfaces, integrating those with the llm and teaching it how to use those tools with a few examples, and then letting it run the show to fulfill the user's ask/question and using the tools…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by thedayisntgray

Mon, 18 Sep 2023 14:16:38 GMT

I've been frustrated by the fact that people still believe that python is some sort of magical default to build LLM apps. It's not. English is the new programming language. White paper for reference: https://arxiv.org/abs/2210.03629 Notice how the prompt used in Langchain (python) https://github.com/langchain-ai/langchain/blob/d21a494a27639... Is the same as it is in Langchain.rb (ruby) https://github.com/andreibondarev/langchainrb/blob/6fc2b962c...

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by thedayisntgray

Mon, 18 Sep 2023 14:07:25 GMT

This also happens to be the same prompt in langchain. This is an implementation of this white paper: https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by krychu

Mon, 10 Jul 2023 07:10:31 GMT

Chain of thought: https://arxiv.org/abs/2201.11903 ReAct: https://arxiv.org/abs/2210.03629 Reflexion: https://arxiv.org/abs/2303.11366 Tree of thoughts: https://arxiv.org/abs/2305.10601 Good video on "Tree of thoughts" which also reviews / puts it in the context of other methods: https://www.youtube.com/watch?v=ut5kp56wW_4 Completion vs conversational interface is something you can read about in the OpenAI API documentation. For the remaining things I don't have single specific pointer at hand.

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by famouswaffles

Tue, 27 Jun 2023 21:16:46 GMT

>GPT cannot function in any environment on its own. Except in response to a direct instruction it cannot plan, it cannot take action, it cannot learn, it cannot adjust to changing circumstance. Sure it can. It's not default behavior sure but it's fairly trivial to set up, just expensive. Gpt-4 can loop on its "thoughts" and reflect, it can take actions in the real world. https://tidybot.cs.princeton.edu/ https://arxiv.org/abs/2304.03442 https://arxiv.org/abs/2210.03629 https://arxiv.org/abs/2303.11366

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by flakiness

Fri, 26 May 2023 21:03:58 GMT

Note that the repo author != the paper author. The research itself [1] seems legit. The paper author also wrote a paper called ReAct [2], which is one of the core components of the langchain framework. * [1] https://arxiv.org/abs/2305.10601 * [2] https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by Veen

Sat, 13 May 2023 09:29:45 GMT

It's problematic for the same reason other injection attacks are. It allows an attacker to get their "code" running in what should be a privileged environment you control. In this case, the "code" is a natural language prompt, but the principle applies. Think about what would happen if an app scraped a web page on which someone had placed instructions for an LLM. The app then passes the instructions as context to the LLM, which is using the ReAct model [0] so it can run code, communicate with other apps, download content from the web, and so on. It's dangerous even if the LLM is just…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by jasonjmcghee

Wed, 10 May 2023 15:58:31 GMT

Yes- being able to reflect on its own thoughts. You could argue being able to observe and think about what was just said aligns with ReAct (https://arxiv.org/pdf/2210.03629.pdf) - maybe a tweak to directly assessing a previous thought, and modifying output / thought process based on the assessment accordingly would help, but I'm not sure that's quite enough. If it can't ask "why" and step back through why it thinks something, I think we'll keep having the confident hallucination problem- rather than "I don't know". But maybe that's touching on the quality of AGI. Is "reasoning" a necessity…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by 1023bytes

Tue, 02 May 2023 06:29:01 GMT

A lot of this can be solved by using clever prompting and allowing the LLM to use external tools - see the ReAct paper https://arxiv.org/abs/2210.03629 I believe OpenAI is going to introduce this to ChatGPT soon as they launch the plugin system.

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by senko

Sun, 09 Apr 2023 23:27:54 GMT

There is ongoing promising work that shows this can be improved a lot: https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by cube2222

Tue, 04 Apr 2023 23:06:00 GMT

Cool stuff. I think agents are the most promising and potentially revolutionary part of the current LLM developments. Moreover, they're quite easy to write yourself, you don't need something like Langchain, the prompt structure is simple and it's a bit of text templating (it's all based on the ReAct paper[0]). That said, the bit about "The trick to avoid hallucination" in the attached blog post is a very neat idea. Obvious in hindsight, as it often is: > So the trick is that we send a stop pattern which in this case is when we see Observation: in it’s output, because then it has created a…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by Sol-

Tue, 04 Apr 2023 05:19:05 GMT

I think the ReAct paper also popularized this approach: https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by kcorbitt

Tue, 28 Mar 2023 17:07:56 GMT

Hey HN! My brother Arctic_fly and I spent the last two weeks since the GPT-4 launch building Taxy, an open source Chrome extension that lets you automate arbitrary tasks in your browser using GPT-4. You can see a few demos in the Github README, but basically it works like this: 1. You open the extension and write the task you'd like done (eg. "schedule a meeting with David tomorrow at 2"). 2. Taxy pulls the DOM of the current page, puts it through a pipeline to remove all non-semantic information, hidden elements, etc and sends it to GPT-4 along with your text instructions. 3. GPT-4 tries to…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by cs702

Tue, 14 Mar 2023 17:38:38 GMT

LLMs will eventually make a lot of simpler machine-learning models obsolete. Imagine feeding a prompt akin to the one below to GPT5, GPT6, etc.: prompt = f"The guidelines for recommending products are: {guidelines}. The following recommendations led to incremental sales: {sample_successes}. The following recommendations had no measurable impact: {sample_failures}. Please make product recommendations for these customers: {customer_histories}. Write a short note explaining your decision for each recommendation." product_recommendations = LLM(prompt) To me, this kind of use of LLMs looks...…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by cs702

Sat, 11 Mar 2023 22:57:06 GMT

There's evidence that you can get LLMs to write chain-of-thought explanations that are consistent with the instructions in the given text, including quantitative data, cohort performance, governance imperatives, qualitative considerations, etc. The models can even be given directions to write conditional approvals if necessary. To get a sense of what is and will be possible, take a look at the ReAct paper: https://arxiv.org/abs/2210.03629 and some of the LangChain tutorials that use it: https://langchain.readthedocs.io/en/latest/modules/agents/ge...…

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by cs702

Sat, 11 Mar 2023 22:49:19 GMT

> Is there any evidence or reason to suspect that this would result in the desired effect? Yes. There's evidence that you can get these models to write chain-of-thought explanations that are consistent with the instructions in the given text. For example, take a look at the ReAct paper: https://arxiv.org/abs/2210.03629 and some of the LangChain tutorials that use it: https://langchain.readthedocs.io/en/latest/modules/agents/ge... https://langchain.readthedocs.io/en/latest/modules/agents/im...

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — mentioned by iandanforth

Fri, 10 Mar 2023 13:32:39 GMT

This feels like it owes more to LangChain than a link at the bottom of the page. Compare their prompt: https://github.com/microsoft/visual-chatgpt/blob/main/visual... With that of the LangChain ReAct conversational agent: https://github.com/hwchase17/langchain/blob/master/langchain... Also it seems appropriate to cite the original ReAct paper (from Google mainly) https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Mon, 06 Feb 2023 00:00:01 GMT

ReAct – interesting paper on LLM prompt engineering

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReAct: Synergizing Reasoning and Acting in Language Models — HN submission

Sun, 01 Jan 2023 22:53:27 GMT

ReAct: Synergizing Reasoning and Acting in Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.