We have 5 of 6 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.
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obscures relevant evidence, making focused reasoning increasingly difficult. We introduce TreeFlex, a framework in which th...
As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML). In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution...
This work introduces ToolMLBench, a suite of executable tools for data inspection, code verification, and experiment diagnosis, together with an SFT and RL pipeline for learning their use, and measures how privileged context changes the likelihood of a sampled tool action and uses this difference as a turn-level reward...
Persistent-negative adversarial distillation consistently improves performance over current methods at matched discriminator compute and yields smoother fresh-policy discriminator trajectories, with fewer below-chance dips.
Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, advisor-only guidance, and general retrieval, and general retrieval and that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retriev...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
