collaborators

5 papers

cs.CL2026

DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking

Tianyi Hu, Niket Tandon, Akhil Arora

Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer. This assumption overlooks open-ended information-seeking scenarios w…

cs.AI2026

Voting with the Graph: Stable RLAIF via Topological Consistency Maximization

Boyin Liu, Zhuo Zhang, Sen Huang +8

Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement er…

cs.LG2026

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Yiju Guo, Tianyi Hu, Zexu Sun +1

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low s…

cs.AI2026

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees

Tianyi Hu, Qingxu Fu, Yanxi Chen +2

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified…

cs.AI2026

JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG

Yiqun Chen, Erhan Zhang, Tianyi Hu +8

The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reas…