We have 9 of 71 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contribution of individual decisions. Step-level credit assignment provides finer-grained supervision, but its estimates can be unreliable because observed returns also depend on s...
The results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system.
This work proposes MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA, and introduces a reasoning-based evidence locator trained with Self-reflective Hint Policy Optimization, which performs progressive refinement by extracting query-relevant fragments within memory units to s...
gui-PRA is introduced, a Process Reward Agent that transforms GUI process evaluation from passive scoring into active investigation, and demonstrates strong competitiveness against fully trained critic models.
Results show that TRACE converts high model potential into stable, consistent performance gain, and bridge the gap between potential and reliable performance to just 4.0 points.
GSAR (Goal-State-Anchor Reward), a RL reward framework that supports scalable task generation and delivers reliable reward signals for stable and efficient policy optimization, is introduced.
This work studies reference-free post-training for multilingual machine translation with open large language models and finds that on-policy distillation reaches, but does not surpass, the quality frontier achieved by RL with checkpoint interpolation.
See, a two-stage data synthesis framework consisting of an efficient exploration stage that builds an explicit UI transition graph over screens and elements, and a graph-based synthesis stage that composes diverse multi-step trajectories via planning and controlled sampling, yields reproducible and explainable data gen...
G-ReAct is a reasoning framework for deep search that organizes reasoning as state evolution over a fixed-topology query graph, transforming exploratory search driven by textual history into graph-guided reasoning under explicit constraints.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
