2 citations · 6 across the 20 of their papers we have counts for
23 papers
KUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative Recommendation
Jiangxia Cao, Hao Peng, Wenlong Xu +97
Generative recommendation, has been attracted a surge of attentions in industrial and academic research community, towards to build more smart system to build next-generation recom…
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
Shouli Wang, Yanfeng Jia, Zhihao Ou +6
During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
Yunjia Qi, Zehua Yin, Xintong Shi +10
LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to…
OneReason Technical Report
OneRec Team, Biao Yang, Boyang Ding +81
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. Howev…
Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?
Yangda Peng, Yunjia Qi, Haotian Xia +8
Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliability of LaaJ for rubric sco…
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3
Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit latent biases in t…
StoryAlign: Evaluating and Training Reward Models for Story Generation
Haotian Xia, Hao Peng, Yunjia Qi +4
Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, sto…
WildReward: Learning Reward Models from In-the-Wild Human Interactions
Hao Peng, Yunjia Qi, Xiaozhi Wang +3
Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deplo…
On the Paradoxical Interference between Instruction-Following and Task Solving
Yunjia Qi, Hao Peng, Xintong Shi +5
Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed. However, we reveal a counter…
StoryWriter: A Multi-Agent Framework for Long Story Generation
Haotian Xia, Hao Peng, Yunjia Qi +4
Long story generation remains a challenge for existing large language models (LLMs), primarily due to two main factors: (1) discourse coherence, which requires plot consistency, lo…
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Hao Peng, Yunjia Qi, Xiaozhi Wang +3
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. H…
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
Yunjia Qi, Hao Peng, Xiaozhi Wang +5
Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications. Growing research efforts aim to develop LLM-based agents to address practic…
MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark
Shengkun Ma, Hao Peng, Lei Hou +1
Machine Reading Comprehension (MRC) is an essential task in evaluating natural language understanding. Existing MRC datasets primarily assess specific aspects of reading comprehens…
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Hao Peng, Yunjia Qi, Xiaozhi Wang +4
Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences…
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
Yushi Bai, Shangqing Tu, Jiajie Zhang +9
This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world…
Pre-training Distillation for Large Language Models: A Design Space Exploration
Hao Peng, Xin Lv, Yushi Bai +4
Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. Previous work applying KD in the field of large language models (LLMs)…
Constraint Back-translation Improves Complex Instruction Following of Large Language Models
Yunjia Qi, Hao Peng, Xiaozhi Wang +3
Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc. Following the conventional instruction-tuning practice, previous works…
OpenEP: Open-Ended Future Event Prediction
Yong Guan, Hao Peng, Xiaozhi Wang +2
Future event prediction (FEP) is a long-standing and crucial task in the world, as understanding the evolution of events enables early risk identification, informed decision-making…
MAVEN-Fact: A Large-scale Event Factuality Detection Dataset
Chunyang Li, Hao Peng, Xiaozhi Wang +4
Event Factuality Detection (EFD) task determines the factuality of textual events, i.e., classifying whether an event is a fact, possibility, or impossibility, which is essential f…
Event GDR: Event-Centric Generative Document Retrieval
Yong Guan, Dingxiao Liu, Jinchen Ma +4
Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering signifi…
ADELIE: Aligning Large Language Models on Information Extraction
Yunjia Qi, Hao Peng, Xiaozhi Wang +3
Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs no…
Event-level Knowledge Editing
Hao Peng, Xiaozhi Wang, Chunyang Li +5
Knowledge editing aims at updating knowledge of large language models (LLMs) to prevent them from becoming outdated. Existing work edits LLMs at the level of factual knowledge trip…
Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation
Hongyin Zhu, Hao Peng, Zhiheng Lyu +3
Existing technologies expand BERT from different perspectives, e.g. designing different pre-training tasks, different semantic granularities, and different model architectures. Few…