feat(bench): update to run researchtown

[lwaekfjlk]

Closes #

📑 Description

✅ Checks

• My pull request adheres to the code style of this project
• My code requires changes to the documentation
• I have updated the documentation as required
• All the tests have passed
• Branch name follows type/descript (e.g. feature/add-llm-agents)
• Ready for code review

ℹ Additional Information

[codecov]

Codecov Report

Attention: Patch coverage is 2.10526% with 93 lines in your changes missing coverage. Please review.

Project coverage is 68.91%. Comparing base (159a725) to head (87b0725).

Files with missing lines	Patch %	Lines
research_bench/proposal_writing.py	0.00%	81 Missing ⚠️
research_bench/run_eval.py	0.00%	9 Missing ⚠️
...arch_town/envs/env_proposal_writing_without_rag.py	0.00%	2 Missing ⚠️
research_town/utils/sampler.py	50.00%	1 Missing ⚠️

@@            Coverage Diff             @@
##             main     #912      +/-   ##
==========================================
- Coverage   70.15%   68.91%   -1.25%     
==========================================
  Files          80       80              
  Lines        3569     3632      +63     
==========================================
- Hits         2504     2503       -1     
- Misses       1065     1129      +64     

Files with missing lines	Coverage Δ
research_town/utils/model_prompting.py	100.00% <100.00%> (ø)
research_town/utils/sampler.py	88.46% <50.00%> (-7.38%)	⬇️
...arch_town/envs/env_proposal_writing_without_rag.py	30.76% <0.00%> (+0.58%)	⬆️
research_bench/run_eval.py	0.00% <0.00%> (ø)
research_bench/proposal_writing.py	0.00% <0.00%> (ø)