├── LICENSE.txt ├── README.md ├── assets ├── application.png ├── cross_heatmap.png ├── framework.png ├── info.png ├── performance.png ├── performance_e2e.jpg ├── performance_sub.jpg ├── query.png ├── retriever.png └── upper_gain.png ├── config.py ├── grpo_loss.py ├── main_grpo_v0.py ├── main_grpo_v1.py ├── module_test ├── __init__.py ├── test_grpo.py ├── test_grpo_diff.py └── test_rollout.py ├── refer_llm ├── __init__.py ├── refer_client.py ├── refer_server.py └── tensor_utils.py ├── requirements.txt ├── retrieval ├── retrieval_bm25.py └── retrieval_e5.py ├── rewards ├── __init__.py └── reward_QAgent.py ├── rollout ├── __init__.py ├── base_rollout.py └── rollout_QAgent.py ├── run.py ├── run.sh └── tools.py /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/README.md -------------------------------------------------------------------------------- /assets/application.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/application.png -------------------------------------------------------------------------------- /assets/cross_heatmap.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/cross_heatmap.png -------------------------------------------------------------------------------- /assets/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/framework.png -------------------------------------------------------------------------------- /assets/info.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/info.png -------------------------------------------------------------------------------- /assets/performance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/performance.png -------------------------------------------------------------------------------- /assets/performance_e2e.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/performance_e2e.jpg -------------------------------------------------------------------------------- /assets/performance_sub.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/performance_sub.jpg -------------------------------------------------------------------------------- /assets/query.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/query.png -------------------------------------------------------------------------------- /assets/retriever.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/retriever.png -------------------------------------------------------------------------------- /assets/upper_gain.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/assets/upper_gain.png -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/config.py -------------------------------------------------------------------------------- /grpo_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/grpo_loss.py -------------------------------------------------------------------------------- /main_grpo_v0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/main_grpo_v0.py -------------------------------------------------------------------------------- /main_grpo_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/main_grpo_v1.py -------------------------------------------------------------------------------- /module_test/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /module_test/test_grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/module_test/test_grpo.py -------------------------------------------------------------------------------- /module_test/test_grpo_diff.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/module_test/test_grpo_diff.py -------------------------------------------------------------------------------- /module_test/test_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/module_test/test_rollout.py -------------------------------------------------------------------------------- /refer_llm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /refer_llm/refer_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/refer_llm/refer_client.py -------------------------------------------------------------------------------- /refer_llm/refer_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/refer_llm/refer_server.py -------------------------------------------------------------------------------- /refer_llm/tensor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/refer_llm/tensor_utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/requirements.txt -------------------------------------------------------------------------------- /retrieval/retrieval_bm25.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/retrieval/retrieval_bm25.py -------------------------------------------------------------------------------- /retrieval/retrieval_e5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/retrieval/retrieval_e5.py -------------------------------------------------------------------------------- /rewards/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rewards/reward_QAgent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/rewards/reward_QAgent.py -------------------------------------------------------------------------------- /rollout/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rollout/base_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/rollout/base_rollout.py -------------------------------------------------------------------------------- /rollout/rollout_QAgent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/rollout/rollout_QAgent.py -------------------------------------------------------------------------------- /run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/run.py -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/run.sh -------------------------------------------------------------------------------- /tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LivingFutureLab/QAgent/HEAD/tools.py --------------------------------------------------------------------------------