Skip to content

merge main#1272

Closed
Hoder-zyf wants to merge 16 commits intoyifei/ablation_researchfrom
main
Closed

merge main#1272
Hoder-zyf wants to merge 16 commits intoyifei/ablation_researchfrom
main

Conversation

@Hoder-zyf
Copy link
Collaborator

@Hoder-zyf Hoder-zyf commented Oct 21, 2025

Description

Motivation and Context

How Has This Been Tested?

  • If you are adding a new feature, test on your own test scripts.

Screenshots of Test Results (if appropriate):

  1. Your own tests:

Types of changes

  • Fix bugs
  • Add new feature
  • Update documentation

📚 Documentation preview 📚: https://RDAgent--1272.org.readthedocs.build/en/1272/

you-n-g and others added 16 commits September 13, 2025 10:25
* feat: init pydantic ai agent & context 7 mcp

* feat: integrate MCP documentation search into data science pipeline evaluation

* fix: disable MCP documentation search and update related docstrings and defaults

* lint

* fix: correct prompt formatting and conditional blocks in pipeline_eval section

* lint

* feat: add query method to PAIAgent for synchronous agent execution

* fix: apply nest_asyncio for agent and update context7 query method

* lint

* lint

* lint

* lint

* docs: update MCP folder docstring and rename test class in test_pydantic.py

* refactor: centralize completion kwargs logic and update pydantic_ai integration

* fixbug

* typo

* fix: bug triggered by padantic-ai version backtracking.

---------

Co-authored-by: Linlang <Lv.Linlang@hotmail.com>
* fix: add json format response fallback to prompt templates

* more json prompt
* chore: add medal info

* return sota_exp_stat

* update hit check

* update experiment

* udpate experiment

* extract log

* remove old log folder

* update candidates

* keep highest score

* early stop if no medal candidate
* feat: add interactor classes and user interaction handling for experiments

* update code

* use fragment retry mechanism instead of rerun()

* fix a bug

* integrate user instructions into proposal and coder

* fix CI

* fix CI

* feat: add approval option for user instructions submission

* feat: enhance user instructions handling in Task and DSExperiment classes

* fix CI

* add user instructions into hypothesis rewrite

* add interface to command line

---------

Co-authored-by: Bowen Xian <xianbowen@outlook.com>
* feat: update README with latest news and announcements

* update readme
* fix: add hypotheses_candidates
* Fix model/factor experiment filtering in Qlib proposals

* fix(dockerfile): install coreutils to resolve timeout command error (#1260)

* chore: remove unused experiment_list and target_list from Qlib proposals

* fix CI

* fix target list

---------

Co-authored-by: Xu Yang <peteryang@vip.qq.com>
* init mcts class

* full ver of MCTS

* auto-lint

* make MCTS feedback in exp-gen()

* refactor: move reset logic from Trace to ExpGen and update usage accordingly

* fix: reinitialize trace on consecutive errors in DataScienceRDLoop

* feat: add reset method to BaseScheduler and call in MCTSScheduler reset

* style: reorder imports for consistency and PEP8 compliance

* lint

* fix observe_feedback

* fix bug

* remove uncommited_rec_status

* more simple

* refactor: move commit observation logic to process_uncommitted_nodes method

* docs: add TODO comment about rule-based virtual root node expansion

* add score reward

* fix bug

* fix small bug

* lint

* change reward

* lint

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: jingyuanlm <842442862@qq.com>
Co-authored-by: amstrongzyf <amstrongzyf@126.com>
* feat: enable cache in mcp

* refactor: remove redundant setting

* fix: conflicts during installation

---------

Co-authored-by: Linlang <Lv.Linlang@hotmail.com>
* init mcts class

* full ver of MCTS

* auto-lint

* make MCTS feedback in exp-gen()

* refactor: move reset logic from Trace to ExpGen and update usage accordingly

* fix: reinitialize trace on consecutive errors in DataScienceRDLoop

* feat: add reset method to BaseScheduler and call in MCTSScheduler reset

* style: reorder imports for consistency and PEP8 compliance

* lint

* fix observe_feedback

* fix bug

* remove uncommited_rec_status

* more simple

* refactor: move commit observation logic to process_uncommitted_nodes method

* docs: add TODO comment about rule-based virtual root node expansion

* add score reward

* fix bug

* fix small bug

* lint

* change reward

* small small change

* autolint

---------

Co-authored-by: xuangu-fang <xuangufang@gmail.com>
Co-authored-by: Young <afe.young@gmail.com>
* add simple rag mcp

* add rag_agent in expGen v2

* add conf config for research rag

* fix CI

* refactor: move context7 and rag config files to new conf modules

* make rag agent general

* fix CI

---------

Co-authored-by: Young <afe.young@gmail.com>
@Hoder-zyf Hoder-zyf closed this Oct 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

10 participants