Categories

131 个页面

Reading

First Return, Entropy-Eliciting Explore

Reinforcing General Reasoning without Verifiers

GENERALIST REWARD MODELS：FOUND INSIDE LARGE LANGUAGE MODELS

RLPR：EXTRAPOLATING RLVR TO GENERAL DOMAINS WITHOUT VERIFIERS

LAN-AND-ACT：Improving Planning of Agents for Long-Horizon Tasks

WEB AGENTS WITH WORLD MODELS ：LEARNING AND LEVERAGING ENVIRONMENT DYNAMICS IN WEB NAVIGATION

WebEvolver：Enhancing Web Agent Self-Improvement with Coevolving World Model

RLVR-World

agent planning综述

Data Engineering for Scaling Language Models to 128K Context