activity
20232026
most citedDo LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

3 citations · 4 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing

Azal Ahmad Khan, Ammar Ahmed, Zeshan Fayyaz +3

Synchronous reinforcement learning methods such as Group Relative Policy Optimization (GRPO) provide stable and reproducible on-policy training, but they are highly vulnerable to s…

cs.LG2026

HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents

Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou +4

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execut…

cs.LG2025

Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization

Chenliang Li, Adel Elmahdy, Alex Boyd +7

Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipe…

cs.LG2025

Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach

Xinnan Zhang, Chenliang Li, Siliang Zeng +6

Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so the…

cs.LG2025

Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment

Quan Wei, Siliang Zeng, Chenliang Li +9

Reinforcement Learning (RL) approaches have been wildly used to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Such…

cs.LG2025

Learning Explainable Dense Reward Shapes via Bayesian Optimization

Ryan Koo, Ian Yang, Vipul Raheja +3

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as…