SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering · HackerPapers discussions

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering — mentioned by diminish

Sun, 24 Aug 2025 10:52:46 GMT

Mini swe agent, as an academic tool, can be easily tested aimed to show the power of a simple idea against any LLM. You can go and test it with different LLMs. Tool calls didn't work fine with smaller LLM sizes usually. I don't see many viable alternatives less than 7GB, beyond Qwen3 4B for tool calling. > right tools allow small models to perform better than undirected tool like bash to do everything. Interesting enough the newer mini swe agent was refutation of this hypothesis for very large LLMs from the original swe agent paper (https://arxiv.org/pdf/2405.15793) assuming that specialized…

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

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering — HN submission

Tue, 17 Sep 2024 07:09:05 GMT

Show HN: Codebased, an AI Search Engine for Code

Codebased combines Tree Sitter for code awareness (find functions, data structures, constants, etc. not just lines of code), full-text search using SQLite, and semantic search using OpenAI embeddings + FAISS. Despite being implemented in Python, supporting semantic search, making multiple API calls for embedding and re-ranking, it is faster than ripgrep for runng searches against the Linux kernel (takes ~1 second vs. ~2 seconds, obviously depends on system, temperature, time of day, tidal forces, etc.) Up next: - A Perplexity-like agent for interpreting results, making multiple follow-up…

17 points; 8 discussion replies on HN. Paper and source history. A submission is not an endorsement.

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering — mentioned by jehna1

Thu, 29 Aug 2024 19:02:37 GMT

Super interesting! Since you're generating code with LLMs, you should check out this paper: https://arxiv.org/pdf/2405.15793 It uses smart feedback to fix the code when LLMs occasionally do hiccups with the code. You could also have a "supervisor LLM" that asserts that the resulting code matches the specification, and gives feedback if it doesn't.

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

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering — HN submission

Tue, 28 May 2024 13:22:56 GMT

SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering

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