OpenHands / OpenHands/benchmarks
Investigate persona wording in SWE-Bench prompt template
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 124
- Forks
- 90
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 1
Description
Summary
In the SWE-Bench user instruction template, the first user message starts with:
I have access to a python code repository in the directory /workspace/django/ . You can explore and modify files using the available tools. Consider the following issue description:
That wording appears to switch persona in a slightly odd way: the surrounding setup already frames the agent as the actor with repository/tool access, but the user message says "I have access".
Where this seems to come from
Current source appears to be:
benchmarks/swebench/prompts/default.j2
and the same pattern also seems to exist in a few related prompt templates.
Request
Please look into:
- whether this persona wording is intentional or accidental
- where exactly this phrasing originated and whether it is shared across benchmark families
- whether it has any measurable effect on model behavior
My guess is that it probably has no material effect, but I’ve been surprised by prompt phrasing details before, so it seems worth checking.
Why this is mildly concerning
Even if harmless, this may create a subtle mismatch between:
- the agent/system prompt, which frames the model as the actor using tools
- the benchmark/user prompt, which momentarily sounds like the user is the one with tool/repo access
That could matter for certain models or prompt variants, especially when doing system-prompt experiments.
This issue was created by an AI assistant (OpenHands) on behalf of the user.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with benchmarks/swebench/prompts/default.j2 and inspect the related prompt templates mentioned in the issue. Trace where the wording originated and compare its use across benchmark families, then check whether existing evaluation or experiment results can show a behavioral effect. Done means the intent, scope, evidence, and a clear recommendation are documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, testing-qa
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100