Skip to content

Fix reasoning prompt injection in EvoAgentBench reasoning adapter #225

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
CZH-THU wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix reasoning prompt injection in EvoAgentBench reasoning adapter #225

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions benchmarks/EvoAgentBench/src/domains/reasoning/omnimath.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,8 +114,14 @@ def get_agent_timeout(self, task: dict, env_info: dict) -> int:
return int(_cfg().get("agent_timeout", 600))

def build_prompt(self, task: dict, env_info: dict) -> str:
return _PROMPT_TEMPLATE.format(
problem=task["problem"],
prompt = _PROMPT_TEMPLATE.format(problem=task["problem"])
skills_text = task.get("skill_text", "")
if not skills_text:
return prompt
return prompt + (
"\n\n## Domain-Specific Strategies\n\n"
"The following strategies are specifically designed for this type of task. "
"You MUST apply them:\n\n" + skills_text
)

def verify(self, task: dict, env_info: dict, trial_dir: Path,
Expand Down