{"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/rlvr-world-training-world-models-with","title":"RLVR-World: Training World Models with Reinforcement Learning","arxiv_id":"2505.13934","date":"2025-05-20","proceeding":null,"authors":["Jialong Wu","Shaofeng Yin","Ningya Feng","Mingsheng Long"],"abstract":"World models predict state transitions in response to actions and are increasingly developed across diverse modalities. However, standard training objectives such as maximum likelihood estimation (MLE) often misalign with task-specific goals of world models, i.e., transition prediction metrics like accuracy or perceptual quality. In this paper, we present RLVR-World, a unified framework that leverages reinforcement learning with verifiable rewards (RLVR) to directly optimize world models for such metrics. Despite formulating world modeling as autoregressive prediction of tokenized sequences, RLVR-World evaluates metrics of decoded predictions as verifiable rewards. We demonstrate substantial performance gains on both language- and video-based world models across domains, including text games, web navigation, and robot manipulation. Our work indicates that, beyond recent advances in reasoning language models, RLVR offers a promising post-training paradigm for enhancing the utility of generative models more broadly.","url_abs":"https://arxiv.org/abs/2505.13934v1","url_pdf":"https://arxiv.org/pdf/2505.13934v1.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":"rlvr-world-training-world-models-with","repo_url":"https://github.com/thuml/RLVR-World","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.13934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13934"}},"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/thuml/RLVR-World","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":12},"by_repo_kind":{"official":{"samples":13,"ran":1,"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":"c4557f6bed96e135","entry":"get_unfinished","repo":"thuml/RLVR-World","repo_kind":"official","path":"lang_wm/webagent/run_for_trajectory.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/run_for_trajectory.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":"c4557f6bed96e135"}},{"code_sha256_prefix":"18ed10ec1a2ccb20","entry":"batch_forward","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/eval_runenv.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/eval_runenv.py","link_basis":"harvester_set","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":"18ed10ec1a2ccb20"}},{"code_sha256_prefix":"e4a5cabcf27fc1f9","entry":"batch_forward","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/train_vgpt.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/train_vgpt.py","link_basis":"harvester_set","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":"e4a5cabcf27fc1f9"}},{"code_sha256_prefix":"ff25903c58c30586","entry":"extract_sections","repo":"thuml/RLVR-World","repo_kind":"official","path":"lang_wm/webagent/agent/world_model_agent.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/agent/world_model_agent.py","link_basis":"harvester_set","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":"ff25903c58c30586"}},{"code_sha256_prefix":"1d6bc3ce11d22b60","entry":"generate_multiple_times","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/train_vgpt.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/train_vgpt.py","link_basis":"harvester_set","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":"1d6bc3ce11d22b60"}},{"code_sha256_prefix":"9fdeb5691f697950","entry":"get_dataloaders","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/eval_runenv.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/eval_runenv.py","link_basis":"harvester_set","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":"9fdeb5691f697950"}},{"code_sha256_prefix":"84199c73adefd0fc","entry":"get_dataloaders","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/eval_vgpt.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/eval_vgpt.py","link_basis":"harvester_set","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":"84199c73adefd0fc"}},{"code_sha256_prefix":"b49a1b06cda0c01a","entry":"get_dataset_path","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/oxe_data_converter.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/oxe_data_converter.py","link_basis":"harvester_set","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":"b49a1b06cda0c01a"}},{"code_sha256_prefix":"93f43874ebbe522a","entry":"get_unfinished","repo":"thuml/RLVR-World","repo_kind":"official","path":"lang_wm/webagent/run_w_world_model.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/run_w_world_model.py","link_basis":"harvester_set","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":"93f43874ebbe522a"}},{"code_sha256_prefix":"3834b388eb788947","entry":"grad_layer_wrt_loss","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/train_ctx_tokenizer.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/train_ctx_tokenizer.py","link_basis":"harvester_set","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":"3834b388eb788947"}},{"code_sha256_prefix":"1825d9e3299f556f","entry":"gradient_penalty","repo":"thuml/RLVR-World","repo_kind":"official","path":"vid_wm/ivideogpt/train_ctx_tokenizer.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/vid_wm/ivideogpt/train_ctx_tokenizer.py","link_basis":"harvester_set","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":"1825d9e3299f556f"}},{"code_sha256_prefix":"37301055029429c8","entry":"parse_task_id_from_path","repo":"thuml/RLVR-World","repo_kind":"official","path":"lang_wm/webagent/run_w_world_model.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/run_w_world_model.py","link_basis":"harvester_set","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":"37301055029429c8"}},{"code_sha256_prefix":"0ef898211b3216e4","entry":"safe_json_load","repo":"thuml/RLVR-World","repo_kind":"official","path":"lang_wm/webagent/agent/world_model_agent.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/agent/world_model_agent.py","link_basis":"harvester_set","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":"0ef898211b3216e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}