5 papers
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Bowen Qin, Yi Xie, Yesheng Liu +1
Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and automated grading. Such rubrics are…
Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents
Bowen Qin, Yi Xie
Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the rep…
PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization
Yingyun Cui, Yi Xie, Piaohong Wang +3
Coding-agent benchmarks have largely measured whether agents can produce functionally correct patches, but production software also demands measurable speedups on real execution ta…
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
Yi Xie, Siao Liu, Falong Fan +3
Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mod…
Modality Dominance-Aware Optimization for Embodied RGB-Infrared Perception
Xianhui Liu, Siqi Jiang, Yi Xie +2
RGB-Infrared (RGB-IR) multimodal perception is fundamental to embodied multimedia systems operating in complex physical environments. Although recent cross-modal fusion methods hav…