collaborators

5 papers

cs.CL2026

Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning

Yongqi Tong, Zhenyu Zhang, Zimi Liu +8

Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this set…

cs.CL2026

STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment

Yongqi Tong, Zhenyu Zhang, Ruirui Wang +6

Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: when should each preference d…

cs.AI2026

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus +5

Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting. This fle…

cs.CL2026

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction

Pan Wang, Yihao Hu, Hang Wang +6

Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many…

cs.CL2026

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel

Chang Liu, Chaoyang Ning, Dayi Jiang +32

Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture int…