Executable Code Actions Elicit Better LLM Agents · HackerPapers discussions

Executable Code Actions Elicit Better LLM Agents — mentioned by amai

Fri, 11 Sep 2026 11:20:41 GMT

The idea to use python code instead of other kinds of tool calls is taken from smolagents: https://huggingface.co/blog/smolagents It is based on this paper https://huggingface.co/papers/2402.01030 and calls this idea CodeAct. The paper is actually from Apple: https://machinelearning.apple.com/research/codeact So Astra and Fable seem to take this idea to the extreme causing some unwanted side-effects.

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

Executable Code Actions Elicit Better LLM Agents — mentioned by ux266478

Tue, 11 Aug 2026 01:41:04 GMT

The "invention" was first published in 2024, by Chinese researchers: https://arxiv.org/abs/2402.01030 Beyond that, it's a trivial batching pattern. Any remotely competent systems engineer developing an agent would immediately reach for it, it's the most basic tool in the toolbox to deal with latency. If Mistral "invested a lot of money in discovering" this, man I'm in the wrong line of work.

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

Executable Code Actions Elicit Better LLM Agents — mentioned by rippeltippel

Mon, 10 Aug 2026 22:11:29 GMT

Isn't that patent similar to CodeAct [1], originally described in this paper [2]? [1] https://learn.microsoft.com/en-us/agent-framework/agents/cod... [2] https://arxiv.org/abs/2402.01030

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

Executable Code Actions Elicit Better LLM Agents — mentioned by anankaie

Mon, 10 Aug 2026 14:54:20 GMT

This is called CodeAct (https://arxiv.org/abs/2402.01030) and is available in a number of frameworks. Patent was applied for 04.03.2026. langgraph-codeact _shipped_ this capability in February.

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

Executable Code Actions Elicit Better LLM Agents — HN submission

Tue, 09 Dec 2025 16:54:07 GMT

Show HN: Construct – API-first coding assistant with CodeAct tool calling

Construct is an open-source AI coding assistant that runs as a gRPC service rather than just a CLI tool. You can run it locally on your laptop or on a remote box, connect multiple clients, disconnect and reconnect without losing context, and integrate it into other tools easily. I wanted something I could leave running and come back to and that is easy to run in a sandbox. Instead of JSON schema, agents write JavaScript to interact with tools. That means they have access to loops, conditionals, error handling, and are encouraged to perform multiple calls in one turn (hundreds in a single turn…

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

Executable Code Actions Elicit Better LLM Agents — mentioned by threecheese

Tue, 02 Dec 2025 20:05:42 GMT

Interesting. Looking through a strategic lens, I feel like this is related to the $1,000 free credit for Claude Code Web (I used a few hundred). What the heck are they aiming for? CodeAct? (https://arxiv.org/abs/2402.01030)

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

Executable Code Actions Elicit Better LLM Agents — mentioned by tucnak

Thu, 21 Aug 2025 09:42:00 GMT

This is insane! We've been training models to write and edit code, and now this? These guys should read this (CodeAct) paper https://arxiv.org/abs/2402.01030 > LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e.g., the scope of pre-defined tools) and restricted flexibility (e.g., inability to compose multiple tools). This work proposes to use executable Python code to consolidate LLM agents' actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct…

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

Executable Code Actions Elicit Better LLM Agents — mentioned by elyase

Thu, 03 Jul 2025 14:01:19 GMT

This is similar to the tool call (fixed code & dynamic params) vs code generation (dynamic code & dynamic params) discussion: tools offer contrains and save tokens, code gives you flexibility. Some papers suggest that generating code is often superior and this will likely become even more true as language models improve [1] https://huggingface.co/papers/2402.01030 [2] https://huggingface.co/papers/2401.00812 [3] https://huggingface.co/papers/2411.01747 I am working on a model that goes a step beyond and even makes the distinction between thinking and code execution unnecessary (it is all…

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

Executable Code Actions Elicit Better LLM Agents — HN submission

Wed, 29 Jan 2025 12:46:01 GMT

Show HN: Gemini 2 with unrestricted code execution

I recently experimented using Gemini 2 Flash and Gemini 2 Flash Thinking with unrestricted code execution in a local sandbox and open sourced the results: https://github.com/gradion-ai/freeact. Here's an example that uses Gemini 2 Flash Thinking as agent that acts via code, executed in a sandbox based on IPython and Docker: https://gist.github.com/krasserm/dcdae47f85ee9922e3284953d07... Gemini's code execution environment is restricted to selected Python libraries like NumPy or SymPy and prevents the model from installing new packages, besides other limitations. While this may be useful for…

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

Executable Code Actions Elicit Better LLM Agents — HN submission

Thu, 30 May 2024 05:17:51 GMT

Executable Code Actions Elicit Better LLM Agents

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