LongVT
[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
파일 탐색기
최종 버전 다운로드 (.zip)- capture.gif
- qr_code.jpg
- teaser.png
- lmms_lab_recipe.py
- tool_reward.py
- vl_agent.py
- video_tools.py
- visual_toolbox.py
- clip_caption.py
- detect_segment.py
- imcott_generate.py
- merge_caption.py
- merge_event.py
- qa_filter_text.py
- qa_filter_vl.py
- qa_generate.py
- text_summary.py
- run_clip_caption.sh
- run_detect_segment.sh
- run_imcott_generate.sh
- run_qa_filter_text.sh
- run_qa_filter_vl.sh
- run_qa_generate.sh
- run_text_summary.sh
- __init__.py
- base_server.py
- mapping.py
- openai.py
- merge_json.py
- split_json_by_team.py
- constant.py
- Makefile
- pyproject.toml
- utils.py
- run_eval.sh
- run_single_inference.sh
- single_inference.py
- tool_call_qwen2_5_vl.jinja
- longvt_7b_rft.yaml
- run_longvt_7b_rft.sh
- longvt_7b_sft.yaml
- run_longvt_7b_sft.sh
- mcp_server.json
- mcp_tool_config.yaml
- timer1_multiturn_grpo.yaml
- timer1_multiturn_grpo_think.yaml
- launch.sh
- longvt_7b_rl_train.sh
- mcp_client.py
- mcp_server.py
- process_time_r1.py
- qwen2_5_vl_chat_template_w_tool.jinja
- aime24_nofigures_agg8.yaml
- aime25_nofigures_agg8.yaml
- utils.py
- charades_reasoning.yaml
- charades_tool.yaml
- utils.py
- _default_template_yaml
- charxiv.yaml
- charxiv_val_descriptive.yaml
- charxiv_val_reasoning.yaml
- constant.py
- utils.py
- _default_template_yaml
- _generate_config.py
- dynamath.yaml
- utils.py
- gpqa_thinking.yaml
- utils.py
- logicvista_thinking.yaml
- utils.py
- longvideobench_no_visual.yaml
- longvideobench_random_choice.yaml
- longvideobench_val_v.yaml
- longvideobench_val_v_tool.yaml
- utils.py
- longvt_no_visual.yaml
- longvt_non_think.yaml
- longvt_reasoning.yaml
- longvt_tool.yaml
- utils.py
- lvbench_no_visual.yaml
- lvbench_random_choice.yaml
- lvbench_reasoning.yaml
- lvbench_tool.yaml
- utils.py
- mathverse_evals.py
- mathverse_testmini.yaml
- utils.py
- _default_template_yaml
- eval_utils.py
- mathvision_reason_test.yaml
- mathvision_reason_testmini.yaml
- utils.py
- mathvista_evals.py
- mathvista_testmini_cot.yaml
- utils.py
- _default_template_yaml
- _generate_config.py
- mmlu_thinking.yaml
- mmlu_thinking_abstract_algebra.yaml
- mmlu_thinking_anatomy.yaml
- mmlu_thinking_astronomy.yaml
- mmlu_thinking_business_ethics.yaml
- mmlu_thinking_clinical_knowledge.yaml
- mmlu_thinking_college_biology.yaml
- mmlu_thinking_college_chemistry.yaml
- mmlu_thinking_college_computer_science.yaml
- mmlu_thinking_college_mathematics.yaml
- mmlu_thinking_college_medicine.yaml
- mmlu_thinking_college_physics.yaml
- mmlu_thinking_computer_security.yaml
- mmlu_thinking_conceptual_physics.yaml
- mmlu_thinking_econometrics.yaml
- mmlu_thinking_electrical_engineering.yaml
- mmlu_thinking_elementary_mathematics.yaml
- mmlu_thinking_formal_logic.yaml
- mmlu_thinking_global_facts.yaml
- mmlu_thinking_high_school_biology.yaml
- mmlu_thinking_high_school_chemistry.yaml
- mmlu_thinking_high_school_computer_science.yaml
- mmlu_thinking_high_school_european_history.yaml
- mmlu_thinking_high_school_geography.yaml
- mmlu_thinking_high_school_government_and_politics.yaml
- mmlu_thinking_high_school_macroeconomics.yaml
- mmlu_thinking_high_school_mathematics.yaml
- mmlu_thinking_high_school_microeconomics.yaml
- mmlu_thinking_high_school_physics.yaml
- mmlu_thinking_high_school_psychology.yaml
- mmlu_thinking_high_school_statistics.yaml
- mmlu_thinking_high_school_us_history.yaml
- mmlu_thinking_high_school_world_history.yaml
- mmlu_thinking_human_aging.yaml
- mmlu_thinking_human_sexuality.yaml
- mmlu_thinking_international_law.yaml
- mmlu_thinking_jurisprudence.yaml
- mmlu_thinking_logical_fallacies.yaml
- mmlu_thinking_machine_learning.yaml
- mmlu_thinking_management.yaml
- mmlu_thinking_marketing.yaml
- mmlu_thinking_medical_genetics.yaml
- mmlu_thinking_miscellaneous.yaml
- mmlu_thinking_moral_disputes.yaml
- mmlu_thinking_moral_scenarios.yaml
- mmlu_thinking_nutrition.yaml
- mmlu_thinking_philosophy.yaml
- mmlu_thinking_prehistory.yaml
- mmlu_thinking_professional_accounting.yaml
- mmlu_thinking_professional_law.yaml
- mmlu_thinking_professional_medicine.yaml
- mmlu_thinking_professional_psychology.yaml
- mmlu_thinking_public_relations.yaml
- mmlu_thinking_security_studies.yaml
- mmlu_thinking_sociology.yaml
- mmlu_thinking_us_foreign_policy.yaml
- mmlu_thinking_virology.yaml
- mmlu_thinking_world_religions.yaml
- utils.py
- _default_template_yaml
- _mmlu_pro.yaml
- mmlu_pro_biology.yaml
- mmlu_pro_business.yaml
- mmlu_pro_chemistry.yaml
- mmlu_pro_computer_science.yaml
- mmlu_pro_economics.yaml
- mmlu_pro_engineering.yaml
- mmlu_pro_health.yaml
- mmlu_pro_history.yaml
- mmlu_pro_law.yaml
- mmlu_pro_math.yaml
- mmlu_pro_other.yaml
- mmlu_pro_philosophy.yaml
- mmlu_pro_physics.yaml
- mmlu_pro_psychology.yaml
- README.md
- utils.py
- _default_template_yaml
- arial.ttf
- mmmu_val_reasoning.yaml
- utils.py
- _default_template_yaml
- mmmu_pro_cot.yaml
- mmmu_pro_standard_cot.yaml
- mmmu_pro_vision_cot.yaml
- utils.py
- mmvu_thinking.yaml
- utils.py
- math_500.yaml
- utils.py
- _default_template_yaml
- utils.py
- videomme_random_choice.yaml
- _default_template_yaml
- utils.py
- videomme.yaml
- videomme_long.yaml
- videomme_no_visual.yaml
- videomme_tool.yaml
- videomme_w_subtitle.yaml
- videomme_w_subtitle_long.yaml
- videomme_w_subtitle_tool.yaml
- _default_template_yaml
- adaptation.yaml
- comprehension.yaml
- perception.yaml
- utils.py
- video_mmmu.yaml
- _default_template_yaml
- adaptation.yaml
- comprehension.yaml
- perception.yaml
- utils.py
- video_mmmu.yaml
- _default_template_yaml
- adaptation.yaml
- adaptation_tool.yaml
- comprehension.yaml
- comprehension_tool.yaml
- perception.yaml
- perception_tool.yaml
- utils.py
- video_mmmu.yaml
- video_mmmu_tool.yaml
- utils.py
- wemath_testmini_thinking.yaml
- create_dataset.py
- README.md
- reward_function.py
- train_grpo.sh
- train_sft.sh
- dapo_trainer.yaml
- dapo_ray_trainer.py
- main_dapo.py
- prepare_dapo_data.sh
- README.md
- run_dapo_early_qwen2.5_32b.sh
- run_dapo_qwen2.5_32b.sh
- run_dapo_wo_ds_qwen2.5_32b.sh
- runtime_env.yaml
- test_dapo_7b.sh
- test_dapo_7b_math.sh
- test_dapo_7b_math_lora.sh
- test_dapo_7b_math_megatron.sh
- test_dapo_dspk_671b_megatron.sh
- test_dapo_qwen3_30b_math.sh
- test_dapo_qwen3_30b_math_single_node.sh
- entropy_trainer.yaml
- __init__.py
- grader.py
- math_normalize.py
- __init__.py
- 32b_clip_cov.sh
- 32b_kl_cov.sh
- 32b_kl_cov_mininbsz.sh
- 7b_clip_cov.sh
- 7b_kl_cov.sh
- entropy_ray_trainer.py
- main_entropy.py
- README.md
- reward.py
- README.md
- reward_function.py
- run_genrm_remote.sh
- agent.yaml
- create_dataset.py
- math_expression.py
- README.md
- run_qwen2.5_3b.sh
- __init__.py
- chat_model.py
- react_agent_loop.py
- test_react_agent_loop.py
- rl_dataset.py
- one_step_off_ppo_megatron_trainer.yaml
- one_step_off_ppo_trainer.yaml
- dapo_7b_math_fsdp2_4_12.sh
- dapo_7b_math_fsdp2_colocate.sh
- dapo_7b_math_megatron_4_12.sh
- dapo_7b_math_megatron_colocate.sh
- fsdp_workers.py
- grpo_0.6b_gsm8k_fsdp2_2_6.sh
- grpo_3b_gsm8k_fsdp2_2_6.sh
- main_ppo.py
- megatron_workers.py
- ray_trainer.py
- README.md
- vllm_sharding_manager.py
- prime_trainer.yaml
- __init__.py
- main_prime.py
- prime_core_algos.py
- prime_dp_rm.py
- prime_fsdp_workers.py
- prime_ray_trainer.py
- run_prime_qwen.sh
- run_prime_qwen_code.sh
- evaluation.yaml
- __init__.py
- gpqa.py
- livecodebench.py
- math.py
- __init__.py
- data_process.py
- main_eval.py
- README.md
- reward_score.py
- run_r1_distill_qwen.sh
- retool.py
- retool_multi_turn_sft_preprocess.py
- retool_sft_preprocess.py
- run_qwen2-32b_sft.sh
- run_qwen2.5_32b_sp8.sh
- run_qwen2.5_7b_sp4.sh
- run_qwen3_4b_sp4.sh
- sandbox_fusion_tool_config.yaml
- spin_trainer.yaml
- core_algos.py
- dp_actor.py
- fsdp_workers.py
- main_spin.py
- README.md
- run_spin.sh
- spin_trainer.py
- sppo_trainer.yaml
- __init__.py
- dp_actor.py
- main_sppo.py
- README.md
- run_qwen2.5-7b_rm.sh
- sppo_ray_trainer.py
- sppo_worker.py
- README.md
- __init__.py
- converter_hf_to_mcore.py
- diagnose.py
- generate_trainer_config.sh
- init_random_model.py
- install_vllm_sglang_mcore.sh
- legacy_model_merger.py
- print_cfg.py
- rollout_viewer.py
- agent_utils.py
- test_basic_agent_loop.py
- __init__.py
- test_gsm8k_interaction.py
- test_interaction_registry.py
- test_transformer.py
- test_transformers_ulysses.py
- test_decorator.py
- main.py
- client.py
- README.md
- run.sh
- server.py
- __init__.py
- test_auto_padding_on_cpu.py
- test_colocated_workers.py
- test_colocated_workers_fused.py
- test_data_transfer.py
- test_decorator_on_cpu.py
- test_driverfunc_to_worker.py
- test_fused_workers_on_cpu.py
- test_high_level_scheduling_api.py
- test_ray_collectives.py
- test_ray_local_envs_on_cpu.py
- test_ray_utils_on_cpu.py
- test_rvdz.py
- test_worker_group_basics.py
- test_worker_group_torch.py
- README.md
- run_all.sh
- test_fsdp_ckpt.py
- test_tensor_dict.py
- __init__.py
- task.py
- tokenizer.py
- __init__.py
- run_gen_qwen05.sh
- qwen2moe_minimal.json
- run_function_reward.sh
- run_model_reward.sh
- run_single_gpu.sh
- run_single_gpu_with_engine.sh
- run_sft.sh
- test_sp_loss_match.py
- __init__.py
- check_custom_rwd_fn.py
- check_results.py
- README.md
- run_dapo.sh
- run_genrm_remote.sh
- run_geo3k_fsdp_sgl_multiturn_w_tool.sh
- run_grpo_lora_with_merge.sh
- run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh
- run_gsm8k_fsdp_sgl_multiturn_w_tool.sh
- run_one_step_off_policy.sh
- run_ppo_trainer_megatron.sh
- run_prime.sh
- run_r1_distill_qwen_aime24_eval.sh
- run_spin.sh
- run_sppo.sh
- run_test.sh
- run_qwen2_5_05b_dapo.sh
- run_qwen2_5_05b_grpo.sh
- run_qwen2_5_05b_sft_peft_sp2.sh
- run_qwen2_5_vl_3b_npu.sh
- check_api_docs.py
- check_device_api_usage.py
- check_docs_time_info.py
- check_docstrings.py
- check_license.py
- check_pr_description.py
- check_pr_title.py
- test_config_docs.py
- test_import.py
- type_coverage_check.py
- validate_imported_docs.py
- validate_structure.py
- README.md
- test_memory_buffers.py
- test_base_tool_on_cpu.py
- __init__.py
- legacy_ppo_megatron_trainer.yaml
- legacy_ppo_trainer.yaml
- test_algo_config_on_cpu.py
- test_critic_config_on_cpu.py
- test_legacy_config_on_cpu.py
- __init__.py
- test_core_algos_on_cpu.py
- test_metric_utils_on_cpu.py
- __init__.py
- test_esi_save_ckpt_on_cpu.py
- test_create_rl_sampler_on_cpu.py
- test_multiturn_sft_dataset_on_cpu.py
- test_rl_dataset_on_cpu.py
- test_sft_dataset_on_cpu.py
- test_pipeline_parallel.py
- test_sandbox_fusion_on_cpu.py
- test_sandbox_on_cpu.py
- _test_module.py
- test_activation_offload.py
- test_config_on_cpu.py
- test_flops_counter.py
- test_fs_on_cpu.py
- test_import_utils_on_cpu.py
- test_linear_cross_entropy.py
- test_linear_cross_entropy_tp.py
- test_model_on_cpu.py
- test_nvtx_profile.py
- test_rollout_trace_on_cpu.py
- test_seqlen_balancing.py
- test_temp_env_on_cpu.py
- test_timeout_decorator_cpu.py
- test_torch_functional.py
- test_registry_on_cpu.py
- vllm_async_rollout.py
- mcp_server.json
- mcp_tool_config
- sandbox_fusion_tool_config
- search_tool_config
- run_fsdp_vllm.py
- test_vllm_chat_scheduler.py
- test_vllm_model_rope_scaling.py
- test_vllm_spmd.py
- async_rollout_utils.py
- test_async_sglang_server.py
- test_custom_completion_callback.py
- test_hf_rollout.py
- test_sglang_async_rollout_mcp_tools.py
- test_sglang_async_rollout_multimodal_delta.py
- test_sglang_async_rollout_search_tools.py
- test_sglang_async_rollout_sf_tools.py
- test_sglang_async_rollout_w_interaction.py
- test_sglang_async_rollout_w_tools.py
- test_sglang_multi_interaction.py
- test_sglang_rollout_sharding_manager.py
- test_sglang_spmd.py
- utils_sglang.py
- __init__.py
- kill_github_tests.sh
- README.md
- test_base_config_on_cpu.py
- test_protocol_on_cpu.py
- __init__.py
- agent_loop.py
- single_turn_agent_loop.py
- tool_agent_loop.py
- tool_parser.py
- __init__.py
- sampler.py
- __init__.py
- dynamicgen_dataset.py
- __init__.py
- __init__.py
- interaction_registry.py
- __init__.py
- base.py
- gsm8k_interaction.py
- __init__.py
- __main__.py
- base_model_merger.py
- fsdp_model_merger.py
- megatron_model_merger.py
- __init__.py
- llama_loader.py
- llama_loader_depracated.py
- llama_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_llama_megatron.py
- __init__.py
- __init__.py
- attention.py
- model.py
- rope_utils.py
- vision_config.py
- vision_model.py
- vision_transformer_block.py
- __init__.py
- config_converter.py
- loader.py
- mbridge.py
- model_forward.py
- model_forward_fused.py
- model_initializer.py
- patch_v012.py
- readme.md
- registry.py
- saver.py
- util.py
- weight_converter.py
- __init__.py
- qwen2_loader.py
- qwen2_loader_depracated.py
- qwen2_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_qwen2_megatron.py
- __init__.py
- __init__.py
- dense_common.py
- kimi_vl.py
- llama.py
- monkey_patch.py
- npu_patch.py
- qwen2.py
- qwen2_5_vl.py
- qwen2_vl.py
- __init__.py
- README.md
- registry.py
- weight_loader_registry.py
- __init__.py
- worker.py
- worker_group.py
- __init__.py
- ray.py
- __init__.py
- decorator.py
- worker.py
- worker_group.py
- __init__.py
- base.py
- megatron.py
- __init__.py
- __init__.py
- parallel_state.py
- __init__.py
- __init__.py
- McpClientManager.py
- utils.py
- __init__.py
- search_r1_like_utils.py
- tool_registry.py
- __init__.py
- base_tool.py
- geo3k_tool.py
- gsm8k_tool.py
- mcp_base_tool.py
- mcp_search_tool.py
- sandbox_fusion_tools.py
- schemas.py
- search_tool.py
- actor.yaml
- dp_actor.yaml
- megatron_actor.yaml
- critic.yaml
- dp_critic.yaml
- megatron_critic.yaml
- legacy_data.yaml
- npu_profile.yaml
- dp_ref.yaml
- megatron_ref.yaml
- ref.yaml
- dp_reward_model.yaml
- megatron_reward_model.yaml
- reward_model.yaml
- rollout.yaml
- __init__.py
- _generated_ppo_megatron_trainer.yaml
- _generated_ppo_trainer.yaml
- algorithm.py
- config.py
- evaluation.yaml
- generation.yaml
- ppo_megatron_trainer.yaml
- ppo_trainer.yaml
- sft_trainer.yaml
- __init__.py
- core_algos.py
- metric_utils.py
- ray_trainer.py
- reward.py
- __init__.py
- constants_ppo.py
- fsdp_sft_trainer.py
- main_eval.py
- main_generation.py
- main_ppo.py
- runtime_env.yaml
- __init__.py
- checkpoint_manager.py
- fsdp_checkpoint_manager.py
- megatron_checkpoint_manager.py
- __init__.py
- multiturn_sft_dataset.py
- README.md
- rl_dataset.py
- rm_dataset.py
- sft_dataset.py
- vision_utils.py
- __init__.py
- performance.py
- trajectory_tracker.py
- __init__.py
- torch_functional.py
- __init__.py
- kernels.py
- linear_cross_entropy.py
- __init__.py
- aggregate_logger.py
- __init__.py
- dist_checkpointing.py
- memory.py
- optimizer.py
- pipeline_parallel.py
- sequence_parallel.py
- tensor_parallel.py
- __init__.py
- utils.py
- __init__.py
- config.py
- empty_annotations.py
- mstx_profile.py
- nvtx_profile.py
- performance.py
- profile.py
- __init__.py
- ray_backend.py
- __init__.py
- README.md
- testing_util.py
- utils.py
- __init__.py
- grader.py
- math_normalize.py
- __init__.py
- utils.py
- __init__.py
- geo3k.py
- gsm8k.py
- math.py
- math_batch.py
- math_dapo.py
- math_verify.py
- search_r1_like_qa_em.py
- __init__.py
- activation_offload.py
- config.py
- device.py
- distributed.py
- flops_counter.py
- fs.py
- fsdp_utils.py
- hdfs_io.py
- import_utils.py
- logging_utils.py
- megatron_utils.py
- memory_buffer.py
- model.py
- net_utils.py
- py_functional.py
- ray_utils.py
- rollout_trace.py
- seqlen_balancing.py
- tokenizer.py
- torch_dtypes.py
- torch_functional.py
- tracking.py
- ulysses.py
- vllm_utils.py
- version
- __init__.py
- base.py
- dp_actor.py
- megatron_actor.py
- __init__.py
- base.py
- dp_critic.py
- megatron_critic.py
- __init__.py
- engine_impl.py
- utils.py
- __init__.py
- engine_impl.py
- __init__.py
- base.py
- __init__.py
- batch.py
- dapo.py
- naive.py
- prime.py
- registry.py
- __init__.py
- reward_model.py
- __init__.py
- base.py
- __init__.py
- actor.py
- critic.py
- __init__.py
- naive_rollout.py
- __init__.py
- async_sglang_server.py
- sglang_rollout.py
- utils.py
- __init__.py
- vllm_async_server.py
- vllm_rollout_spmd.py
- __init__.py
- async_server.py
- base.py
- chat_scheduler.py
- hf_rollout.py
- schemas.py
- tokenizer.py
- __init__.py
- base.py
- fsdp_sglang.py
- fsdp_ulysses.py
- fsdp_vllm.py
- megatron_sglang.py
- megatron_vllm.py
- __init__.py
- fsdp_workers.py
- megatron_workers.py
- __init__.py
- base_config.py
- hermes_tool_parser.py
- protocol.py
- py.typed
- .gitignore
- .pre-commit-config.yaml
- LICENSE
- pyproject.toml
- README.md
- requirements-npu.txt
- requirements.txt
- requirements_reproduce.txt
- requirements_sglang.txt
- setup.py
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/EvolvingLMMs-Lab/LongVT
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd LongVT
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. 공식 설치 스크립트
쉬움 추천사전 준비물
- Python 3 pip 명령어를 쓰려면 Python이 필요합니다.
pip install --no-deps -e .
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
pip install huggingface_hub
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
3. Python
쉬움사전 준비물
pip install --no-deps -e .
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
uv pip install -e .
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
pip install -e .
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
uv pip install -e ".[dev]"
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
pip install huggingface_hub
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
4. Make
보통사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Make Linux/macOS는 보통 기본 설치되어 있습니다. Windows는 별도 설치(예: MSYS2, WSL)가 필요합니다.
cd data
이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.
make
생성된 빌드 설정을 바탕으로 실제 컴파일을 진행해 실행 파일을 만듭니다.
에러 없이 끝나면 성공입니다. 생성된 실행 파일을 직접 실행해보세요.
// repository documentation
Was this content helpful?
(0 ratings)
