5 papers · 1 filter
OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
Junyu Lu, Shichao Weng, Zhiqiang Wang +10
The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We study whether tree search imp…
Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit
Haoxuan Jia, Yang Liu, Yingguang Yang +14
Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they leave machine-readable evide…
The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment
Junyu Lu, Qi Wei, Peishuo Zheng +6
Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have already passed prosecutorial r…
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
Deyi Ji, Junyu Lu, Xuanyi Liu +7
Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aest…
L0: Reinforcement Learning to Become General Agents
Junjie Zhang, Jingyi Xi, Zhuoyang Song +7
Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To addre…