training methods
5 notes, newest first.
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Researchers introduce a new method called Top-K prompting to train language models for single-step retrosynthesis, a crucial component of computer-aided synthesis planning. They use an ultra-large dataset of verified…
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
The paper introduces Visual Skill Cards (VSCs), a memory representation that helps computer agents make decisions by binding reusable procedures with applicability cues, visual evidence, and verification signals. The…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers have proposed a new method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers propose a method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
The authors propose a new training paradigm called PATS for reinforcement learning agents that learn long-term tasks. PATS converts rollout groups from the latest policy into evidence cards and adjusts the context used…
