This work proposes a reinforcement learning framework built around a training environment that integrates human domain knowledge with model reasoning, and instantiates this framework in interactive web application generation, a representative open-ended generation task.
Rui Jin, Jikai Chen, Cheng-Yue Yu et al.· 1 citation
This work proposes a steering agent that supervises execution on the fly and steers the system back on track when drift occurs, and jointly train the two paths with reinforcement learning, combining a pairwise ranking objective with group-relative policy optimization (GRPO).
Le-Yang Shen, Ya-Xin Gong, Yang Zhang et al.· 0 citations
Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream agent.
Ya-Xin Gong, Gang-Yi Zhang, Chong-Ming Gao et al.· 0 citations
CREDO reads the confidence from a dedicated token pair in the model's output distribution and trains it by differentiable regression, turning the trained confidence into a signal for accuracy, weighting rollouts by how far confidence and outcome disagree, so that accuracy and calibration improve together.
Chen-Xiao Fan, Chong-Ming Gao, Gang-Yi Zhang et al.· 0 citations
A reinforcement learning framework that converts rubric-level functional feedback into localized optimization signals over generated code and aligns evaluator-generated textual attributions with responsible code spans and generated tokens is proposed.
Rui Jin, Jikai Chen, Yihang 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.
