7 papers
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
Xintong Li, Sha Li, Yuwei Zhang +8
Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories fo…
SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents
Qianfeng Wen, Yifan Simon Liu, Xin Liu +4
Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that…
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Tianpeng Bu, Xin Liu, Qihua Chen +7
While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation…
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
Hao Jiang, Shurui Li, Tianpeng Bu +7
Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhib…
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Yining Lu, Zilong Wang, Shiyang Li +6
Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thu…
Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
Siqi Guo, Ilgee Hong, Vicente Balmaseda +6
Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being…