update link

you-n-g · you-n-g · commit e48e3ef1e87d · 2024-11-26T02:16:11.000Z
diff --git a/docs/research/benchmark.rst b/docs/research/benchmark.rst
@@ -105,6 +105,5 @@ Related Paper
 
 .. image:: https://github.com/user-attachments/assets/494f55d3-de9e-4e73-ba3d-a787e8f9e841
 
-To replicate the benchmark detailed in the paper, please consult the factors listed in the following file:
-
-    .. file:: ../_static/RD2bench.json
+To replicate the benchmark detailed in the paper, please consult the factors listed in the following file: `RD2bench.json <../_static/RD2bench.json>`_.
+Please note use ``only_correct_format=False`` when evaluating the results.
diff --git a/rdagent/components/coder/factor_coder/eva_utils.py b/rdagent/components/coder/factor_coder/eva_utils.py
@@ -221,7 +221,7 @@ def evaluate(
                     str(resp_dict["output_format_feedback"]),
                     resp_dict["output_format_decision"],
                 )
-            except (KeyError, json.JSONDecodeError ) as e:
+            except (KeyError, json.JSONDecodeError) as e:
                 attempts += 1
                 if attempts >= max_attempts:
                     raise KeyError(

Original file line number	Diff line number	Diff line change
`@@ -221,7 +221,7 @@ def evaluate(`
`221`	`221`	`str(resp_dict["output_format_feedback"]),`
`222`	`222`	`resp_dict["output_format_decision"],`
`223`	`223`	`)`
`224`		`- except (KeyError, json.JSONDecodeError ) as e:`
	`224`	`+ except (KeyError, json.JSONDecodeError) as e:`
`225`	`225`	`attempts += 1`
`226`	`226`	`if attempts >= max_attempts:`
`227`	`227`	`raise KeyError(`