arXiv:2610.02826v1 Announce Type: new
Abstract: Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that m...
By Zongxia Li, Yucheng Shi, Zhongzhi Li, Junyao Yang, Ruhan Wang, Chengsong Huang, Fuxiao Liu, Haitao Mi, Jordan Boyd-Graber, LeoweiLiang
arXiv:2608. 02694v1 Announce Type: cross Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions.
By Lecheng Yan, Jianze Lin, Yichong Zhang, Ben Pan, Wenxi Li, Chenyang Lyu, Liting Zhou, Cathal Gurrin
WorldGuide is a closed‑loop video world model that, given an initial image and a task goal, predicts an atomic action, generates the corresponding video clip, and uses that clip to decide the next action or terminate the task. It trains a Planner to predict the next action or completion from visual progress and an Executor to realize those actions, while a hierarchical visual memory tracks state over long horizons. The authors introduce WorldGuide‑Bench, a dataset of ~59K step‑annotated videos across 245 tasks, and show that WorldGuide outperforms the recent MiniMax‑H3 model on both WorldGuide‑Bench and VideoCraft‑Bench, highlighting the benefit of coupling planning with learned execution for goal‑directed procedural video generation.
By Ankan Deria, Komal Kumar, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan
The study demonstrates that governance records—structured logs linking task contracts, model attempts, verifier decisions, and outputs—can serve as effective supervision for bounded AI models. Using a verifier-selected self‑training approach, the authors show that a Qwen3‑14B model trained on plans accepted by an independent VAL verifier achieved significant gains in plan acceptance across numerous PlanBench replanning cases, outperforming other selection strategies. The results highlight the feasibility of one‑shot execution and cumulative learning without relying on oracle targets or stronger teachers.
By Jesus Salas
The paper investigates how fine‑grained credit assignment affects learning in multimodal agentic reinforcement learning, using video editing as a testbed. Four movie‑trailer editing tasks—Content Selection, Narrative Sequencing, Rough Cut, and Fine Cut—are introduced to represent real‑world editing workflows with varying complexity and horizon lengths. The study finds that decaying process rewards significantly boost performance on the long‑horizon Fine Cut task, while offering modest gains on shorter tasks; however, fixed process‑reward weighting can lead to reward‑hacking and degraded outcomes, and on‑policy self‑distillation provides limited benefit.
By Lei Zhao, Zongheng Cao, Xinyu Hu
StateWise is a method that trains a single large language model to maintain and update its own constraint state during multi‑turn dialogue. By fine‑tuning the model to summarize conversations into a typed state with tombstones for revoked constraints and then self‑training on trajectories that pass exact round‑trip checks, it reduces relapse and improves conversation success. The approach outperforms a compiled‑ledger baseline on relapse without requiring inference‑time scaffolding, and it is evaluated on two backbones with held‑out constraint families and unseen phrasings.
By Samarth Varshney, Ritu Yadav