{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/videoagent-self-improving-video-generation","title":"VideoAgent: Self-Improving Video Generation","arxiv_id":"2410.10076","date":"2024-10-14","proceeding":null,"authors":["Achint Soni","Sreyas Venkataraman","Abhranil Chandra","Sebastian Fischmeister","Percy Liang","Bo Dai","Sherry Yang"],"abstract":"Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be executed. However, a major bottleneck in leveraging video generation for control lies in the quality of the generated videos, which often suffer from hallucinatory content and unrealistic physics, resulting in low task success when control actions are extracted from the generated videos. While scaling up dataset and model size provides a partial solution, integrating external feedback is both natural and essential for grounding video generation in the real world. With this observation, we propose VideoAgent for self-improving generated video plans based on external feedback. Instead of directly executing the generated video plan, VideoAgent first refines the generated video plans using a novel procedure which we call self-conditioning consistency, utilizing feedback from a pretrained vision-language model (VLM). As the refined video plan is being executed, VideoAgent collects additional data from the environment to further improve video plan generation. Experiments in simulated robotic manipulation from MetaWorld and iTHOR show that VideoAgent drastically reduces hallucination, thereby boosting success rate of downstream manipulation tasks. We further illustrate that VideoAgent can effectively refine real-robot videos, providing an early indicator that robotics can be an effective tool in grounding video generation in the physical world.","url_abs":"https://arxiv.org/abs/2410.10076v2","url_pdf":"https://arxiv.org/pdf/2410.10076v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"videoagent-self-improving-video-generation","repo_url":"https://github.com/video-as-agent/videoagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.10076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10076"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/video-as-agent/videoagent","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":5,"ran_violates":4,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":14,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7f1040f5e3991d5e","entry":"identity","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/imagen.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/imagen.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f1040f5e3991d5e"}},{"code_sha256_prefix":"d3c3fae976f3a679","entry":"adaptive_sampling","repo":"video-as-agent/videoagent","repo_kind":"official","path":"sample_dataset_generation.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/sample_dataset_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3c3fae976f3a679"}},{"code_sha256_prefix":"d1ef6b8cb9a28a53","entry":"default","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/goal_diffusion.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/goal_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1ef6b8cb9a28a53"}},{"code_sha256_prefix":"f46bcb6099334fa6","entry":"downsample_2d","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/resnet.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f46bcb6099334fa6"}},{"code_sha256_prefix":"42b1783a347ad0d9","entry":"encode_gif","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/feedback_binary_rf.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/feedback_binary_rf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42b1783a347ad0d9"}},{"code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/feedback_binary_rf.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/feedback_binary_rf.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/imagen.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/imagen.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/goal_diffusion.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/goal_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"3072294c9b32cf4b","entry":"first","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/imagen.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/imagen.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3072294c9b32cf4b"}},{"code_sha256_prefix":"a191f9f21d279753","entry":"rearrange_dims","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/resnet.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a191f9f21d279753"}},{"code_sha256_prefix":"f67b30f563b85481","entry":"tensors2vectors","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/goal_diffusion.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/goal_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f67b30f563b85481"}},{"code_sha256_prefix":"16845e6d52a74742","entry":"chat_with_openai","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/feedback_mw_extend.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/feedback_mw_extend.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16845e6d52a74742"}},{"code_sha256_prefix":"a78c6bc78ae4532c","entry":"chat_with_openai_rf","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/feedback_binary_rf.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/feedback_binary_rf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a78c6bc78ae4532c"}},{"code_sha256_prefix":"31e7ed79c46ee9a9","entry":"upsample_2d","repo":"video-as-agent/videoagent","repo_kind":"official","path":"flowdiffusion/model/resnet.py","file_url":"https://github.com/video-as-agent/videoagent/blob/HEAD/flowdiffusion/model/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31e7ed79c46ee9a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}