5 papers
PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs
Dayang Liang, Liyuan He, Xuan Feng +3
Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants…
AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models
Wentao Zhang, Mingxuan Zhao, Jincheng Gao +5
The rapid advancement of Large Language Models (LLMs) has led to a surge of financial benchmarks, evolving from static knowledge evaluation toward interactive trading simulations.…
Online Causal Kalman Filtering for Stable and Effective Policy Optimization
Shuo He, Lang Feng, Xin Cheng +2
Reinforcement learning for large language models suffers from high-variance token-level importance sampling (IS) ratios, which would destabilize policy optimization at scale. To im…
AgentOCR: Reimagining Agent History via Optical Self-Compression
Lang Feng, Fuchao Yang, Feng Chen +5
Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, but practical deployment is bottlenecke…
Task-Aware Exploration via a Predictive Bisimulation Metric
Dayang Liang, Ruihan Liu, Lipeng Wan +2
Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic…