This work introduces a VLA tool-family interface that exposes explicit tool selection and in-execution progress feedback, enabling efficient event-triggered agent replanning without continuous agent polling and proposes Tool-Aligned Post-Training (TAPT), which constructs invocation-aligned training units for instructio...
ESCD aggregates prefix-related teacher events and supervises the total probability of byte-compatible one-step student completions, avoiding tokenizer-dependent probability splits among individual tokens, and support event entry and event completion as complementary supervision targets for cross-tokenizer knowledge tra...
Jia-Cheng Liu, Jing-Wei Song, Qi-Tuan Zhang et al.· 0 citations
RSI-Master consists of an Experiment OS, which enables regularized experimental actions and maintains persistent, traceable experimental records, and Reviewer-Guided Research Orchestration, which organizes Workers and Reviewers in a dynamically growing research DAG.
Ya-Xin Du, Xi-Yuan Yang, Zhi-Fan Zhou et al.· 1 citation
Answer-Backtracked Credit Assignment (ABC) is proposed, a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant a...
Yi-Jun Lu, Rui Ye, Jia-Jun Wang et al.· 1 citation
By bridging graph topology learning and graph generation, this review provides a broader cross-disciplinary perspective on the field and outlines promising directions for future research.
Xiaowen Dong, Hoi-To Wai, Si-Heng Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
