11 papers
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Zihao Wang, Yiming Li, Yutong Wu +8
LLM-based web agents are increasingly deployed in real-world settings such as e-commerce, where they interact extensively with untrusted web content while executing actions that ca…
CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data
Vipul Gupta, Zihao Wang, Razvan-Gabriel Dumitru +3
Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post train…
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…
Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers
MohammadHossein Rezaei, Anas Mahmoud, Zihao Wang +6
Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LL…
Self-Distilled Agentic Reinforcement Learning
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8
Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon…
FeatCal: Feature Calibration for Post-Merging Models
Yanggan Gu, Shuo Cai, Zihao Wang +7
Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often still underperforms task exper…
Reward Hacking in Rubric-Based Reinforcement Learning
Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang +3
Reinforcement learning with verifiable rewards has enabled strong post-training gains in domains such as math and coding, though many open-ended settings rely on rubric-based rewar…
Dynamic analysis enhances issue resolution
Mingwei Liu, Zihao Wang, Zhenxi Chen +3
Resolving complex code defects from natural language descriptions remains a fundamental software engineering challenge. Recently, large language models (LLMs) have driven the creat…
PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning
Afra Feyza Akyürek, Advait Gosai, Chen Bo Calvin Zhang +21
Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to…
Online Rubrics Elicitation from Pairwise Comparisons
MohammadHossein Rezaei, Robert Vacareanu, Zihao Wang +4
Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work sh…
Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
Junkai Zhang, Zihao Wang, Lin Gui +7
Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality output…