1 citations · 1 across the 17 of their papers we have counts for
18 papers
Rethinking Self-Distillation for Multi-Teacher Capability Merging
Roy Xie, Dan Friedman, Feng Nan +7
Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. Recent tren…
Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers
Yu Wang, Shengyao Zhuang, Xueguang Ma +4
A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with th…
Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget
Zhichao Xu, Xueguang Ma, Shengyao Zhuang +5
Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure av…
PERSONAJUDGE: Simulating Individual Human Preference Judgments with Evaluator-Specific Demonstration Data
Zeyu He, Xuan Qi, Subramanian Chidambaram +4
Large language models increasingly serve as judges in AI evaluation, but current approaches rely on consensus preferences that ignore individual evaluator variation. We propose a n…
Improving Long-Context Retrieval with Multi-Prefix Embedding
Zhenglin Yu, Xueguang Ma, Shengyao Zhuang +4
Long-context retrieval exposes a tension: single-vector embeddings lose fine-grained detail, while token-level multi-vector methods incur prohibitive storage. We propose Multi-Pref…
An Empirical Study of Automating Agent Evaluation
Kang Zhou, Sangmin Woo, Haibo Ding +15
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises:…
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, Bo Yuan, Zhichao Xu +4
We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solv…
Layer-wise Token Compression for Efficient Document Reranking
Shengyao Zhuang, Zhichao Xu, Ivano Lauriola
Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computation…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
Linbo Liu, Guande Wu, Han Ding +7
Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on…
Diffusion Language Model Inference with Monte Carlo Tree Search
Zheng Huang, Kiran Ramnath, Yueyan Chen +8
Diffusion language models (DLMs) have recently emerged as a compelling alternative to autoregressive generation, offering parallel generation and improved global coherence. During…
LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
Zhichao Xu, Shengyao Zhuang, Crystina Zhang +5
While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GP…
Reinforcement Learning for Self-Improving Agent with Skill Library
Jiongxiao Wang, Qiaojing Yan, Yawei Wang +6
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt wh…
A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
Minhua Lin, Zongyu Wu, Zhichao Xu +6
The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static…
SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
Jiazheng Li, Yawei Wang, David Yan +5
Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, a…
Rethinking On-policy Optimization for Query Augmentation
Zhichao Xu, Shengyao Zhuang, Xueguang Ma +6
Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first pr…
Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
Zhichao Xu, Zongyu Wu, Yun Zhou +9
Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent work has begun training LLMs to dynamically pla…
RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
Zhichao Xu, Minheng Wang, Yawei Wang +4
Search agents trained with reinforcement learning (RL) interleave reasoning with tool calls in a multi-turn, tool-integrated reasoning (TIR) loop, where each tool invocation return…