Skip to content

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Doc: Fix dead link to benchmarking

Kilian Lierete483870f2ee6
diff --git a/docs/installation/migration.md b/docs/installation/migration.md
index 4bfe9758..8a9755a1 100644
--- a/docs/installation/migration.md
+++ b/docs/installation/migration.md
@@ -7,6 +7,7 @@ Welcome to SWE-agent 1.0! So much new stuff! Here's a quick rundown of the cool
* :sparkles: Fast, massively parallel code execution with [SWE-ReX](https://github.com/swe-agent/SWE-ReX).
* :sparkles: Run SWE-agent locally but execute code in the cloud (using modal, AWS, or anything else that runs [SWE-ReX](https://github.com/swe-agent/SWE-ReX)).
+* :sparkles: Configurable retry mechanisms: Try multiple agent configurations, models, parameters, etc., then choose the best one.
* :sparkles: Flexible tool definitions with [tool bundles](../config/tools.md).
* :sparkles: All language models supported using `litellm` (see [models](../installation/keys.md)).
* :sparkles: Override any configuration option from the command line (see [command line basics](../usage/cl_tutorial.md)).
diff --git a/mkdocs.yml b/mkdocs.yml
index fefada8a..f844dedc 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -71,7 +71,6 @@ nav:
- "Solving coding challenges": "usage/coding_challenges.md"
- "Trajectory inspector": "usage/inspector.md"
- "Batch mode": "usage/batch_mode.md"
- - "Benchmarking": "usage/benchmarking.md"
- "FAQ": "faq.md"
- User Guides:
- "usage/index.md"