mini-swe-agent is a radically simple Python-based agent from the Princeton and Stanford team behind SWE-bench that uses only bash as its tool, maintains a completely linear message history, and executes each action via independent subprocess.run calls. Despite being roughly 100 lines of core agent code, it scores over 74% on SWE-bench verified and is used by organizations including Meta, NVIDIA, IBM, and Anyscale.
- The core design argument is that as language models grow more capable, elaborate tool scaffolds become unnecessary and the LM itself should drive the shell
- Supports sandboxed deployment via docker, podman, singularity, bwrap, and others; installable from PyPI via uvx, pipx, or pip
- The core design argument is that as language models grow more capable, elaborate tool scaffolds become unnecessary and the LM itself should drive the shell
- Supports sandboxed deployment via docker, podman, singularity, bwrap, and others; installable from PyPI via uvx, pipx, or pip
SWE-bench Verified is a human-filtered subset of 500 instances from SWE-bench created in collaboration with OpenAI to provide a reliable evaluation set for coding agents and language models. Human annotators reviewed each instance to ensure problem descriptions are clear, test patches are correct, and tasks are solvable with available information. The Verified leaderboard shows results from a wide variety of AI coding systems, and a Bash Only view isolates language model performance using mini-SWE-agent in a minimal bash environment.
- Human validation ensures clarity, correctness of test patches, and solvability
- Bash-only comparison uses mini-SWE-agent with ReAct loop, no tools or scaffold
- Leaderboard distinguishes mini-SWE-agent LM results from full agent systems via Agent dropdown
- Release 2.x uses tool calling vs 1.x parses actions from output strings, making releases not directly comparable
- Human validation ensures clarity, correctness of test patches, and solvability
- Bash-only comparison uses mini-SWE-agent with ReAct loop, no tools or scaffold
- Leaderboard distinguishes mini-SWE-agent LM results from full agent systems via Agent dropdown
- Release 2.x uses tool calling vs 1.x parses actions from output strings, making releases not directly comparable
Unsloth AI presents performance benchmarks for Qwen3.6-35B-A3B GGUF quantizations, claiming state-of-the-art results in mean KL divergence across most model sizes. The discussion includes community analysis regarding SWE-bench Verified performance, where some users noted unexpected discrepancies between Qwen3.5 and Qwen3.6 quantization results during coding tasks.
Key points:
- Unsloth ranks first in 21 of 22 model sizes for mean KL divergence.
- Community debate over SWE-bench testing methodology and sample sizes.
- Reported performance variations between different quantization levels (Q4, Q5, Q6, Q8).
- Discussion on system prompt adherence and error rates in coding benchmarks.
Key points:
- Unsloth ranks first in 21 of 22 model sizes for mean KL divergence.
- Community debate over SWE-bench testing methodology and sample sizes.
- Reported performance variations between different quantization levels (Q4, Q5, Q6, Q8).
- Discussion on system prompt adherence and error rates in coding benchmarks.
Qwen3-Coder-Next is an 80-billion-parameter language model that activates only 3 billion parameters during inference, achieving strong coding capabilities through agentic training with verifiable task synthesis and reinforcement learning. It is an open-weight model specialized for coding agents, and both base and instruction-tuned versions are released to support research and real-world coding agent development.
All Hands AI has released OpenHands CodeAct 2.1, an open-source software development agent that can solve over 50% of real GitHub issues in SWE-Bench. The agent uses Anthropic’s Claude-3.5 model, function calling, and improved directory traversal to achieve this milestone.
