README.md
pyproject.toml
grpo_in_sandbox/__init__.py
grpo_in_sandbox/action.py
grpo_in_sandbox/agent.py
grpo_in_sandbox/agent_configs.py
grpo_in_sandbox/agent_factory.py
grpo_in_sandbox/cli.py
grpo_in_sandbox/config.py
grpo_in_sandbox/docker_runtime.py
grpo_in_sandbox/kaggle_runtime.py
grpo_in_sandbox/observation.py
grpo_in_sandbox/runtime.py
grpo_in_sandbox/tools.py
grpo_in_sandbox/train.py
grpo_in_sandbox/trajectory.py
grpo_in_sandbox.egg-info/PKG-INFO
grpo_in_sandbox.egg-info/SOURCES.txt
grpo_in_sandbox.egg-info/dependency_links.txt
grpo_in_sandbox.egg-info/requires.txt
grpo_in_sandbox.egg-info/top_level.txt
grpo_in_sandbox/benchmark/AGENTS.md
grpo_in_sandbox/benchmark/README.md
grpo_in_sandbox/benchmark/agent.md
grpo_in_sandbox/benchmark/runner.py
grpo_in_sandbox/benchmark/biomed/README.md
grpo_in_sandbox/benchmark/biomed/agent.md
grpo_in_sandbox/benchmark/biomed/config.yaml
grpo_in_sandbox/benchmark/biomed/reward.py
grpo_in_sandbox/benchmark/biomed/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/chem/README.md
grpo_in_sandbox/benchmark/chem/agent.md
grpo_in_sandbox/benchmark/chem/config.yaml
grpo_in_sandbox/benchmark/chem/reward.py
grpo_in_sandbox/benchmark/chem/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/demo/README.md
grpo_in_sandbox/benchmark/demo/agent.md
grpo_in_sandbox/benchmark/demo/config.yaml
grpo_in_sandbox/benchmark/demo/data.json
grpo_in_sandbox/benchmark/demo/reward.py
grpo_in_sandbox/benchmark/demo/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/instruct_follow/README.md
grpo_in_sandbox/benchmark/instruct_follow/agent.md
grpo_in_sandbox/benchmark/instruct_follow/config.yaml
grpo_in_sandbox/benchmark/instruct_follow/reward.py
grpo_in_sandbox/benchmark/instruct_follow/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/instruct_pretrain/README.md
grpo_in_sandbox/benchmark/instruct_pretrain/agent.md
grpo_in_sandbox/benchmark/instruct_pretrain/config.yaml
grpo_in_sandbox/benchmark/instruct_pretrain/reward.py
grpo_in_sandbox/benchmark/instruct_pretrain/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/long_context/README.md
grpo_in_sandbox/benchmark/long_context/agent.md
grpo_in_sandbox/benchmark/long_context/config.yaml
grpo_in_sandbox/benchmark/long_context/judge.py
grpo_in_sandbox/benchmark/long_context/reward.py
grpo_in_sandbox/benchmark/long_context/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/math/README.md
grpo_in_sandbox/benchmark/math/agent.md
grpo_in_sandbox/benchmark/math/config.yaml
grpo_in_sandbox/benchmark/math/reward.py
grpo_in_sandbox/benchmark/math/vanilla_llm_prompt.py
grpo_in_sandbox/benchmark/physics/README.md
grpo_in_sandbox/benchmark/physics/agent.md
grpo_in_sandbox/benchmark/physics/config.yaml
grpo_in_sandbox/benchmark/physics/judge.py
grpo_in_sandbox/benchmark/physics/reward.py
grpo_in_sandbox/benchmark/physics/vanilla_llm_prompt.py
grpo_in_sandbox/config/company_team.yaml
grpo_in_sandbox/config/general.yaml
grpo_in_sandbox/config/product_team.yaml
grpo_in_sandbox/config/runtime.example.yaml