74 citations · 120 across the 44 of their papers we have counts for
47 papers
PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents
Pirzada Suhail, Menglin Xia, Xuchao Zhang +3
Memory systems are becoming a core component of LLM agents, but constructing and maintaining memory remains expensive because it relies on repeated calls to large proprietary langu…
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Yuxiao Yang, Tianrun Yu, Shangzhe Li +6
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination…
ActionNex: A Virtual Outage Manager for Cloud Computing
Zhenfeng Lin, Haoji Hu, Ming Hao +11
Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven decisions under partial observabili…
WebXSkill: Skill Learning for Autonomous Web Agents
Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12
Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap in existing skill formulations:…
AutoAdapt: An Automated Domain Adaptation Framework for LLMs
Sidharth Sinha, Anson Bastos, Xuchao Zhang +3
Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily…
Provable and Practical In-Context Policy Optimization for Self-Improvement
Tianrun Yu, Yuxiao Yang, Zhaoyang Wang +6
We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agen…
Budget-Aware Agentic Routing via Boundary-Guided Training
Caiqi Zhang, Menglin Xia, Xuchao Zhang +5
As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable…
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
Menglin Xia, Xuchao Zhang, Shantanu Dixit +6
Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scalin…
Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning
Shangzhe Li, Xuchao Zhang, Chetan Bansal +1
Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without prefer…
Generative Caching for Structurally Similar Prompts and Responses
Sarthak Chakraborty, Suman Nath, Xuchao Zhang +2
Large Language Models (LLMs) are increasingly being used to plan, reason, and execute tasks across diverse scenarios. In use cases like repeatable workflows and agentic settings, p…
SynthAgent: Adapting Web Agents with Synthetic Supervision
Zhaoyang Wang, Yiming Liang, Xuchao Zhang +9
Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address t…
LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
Dongge Han, Camille Couturier, Daniel Madrigal Diaz +3
We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories int…
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Dongge Han, Menglin Xia, Daniel Madrigal Diaz +7
Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs). However, SLMs' limited capacity restricts their reasoning capabilities and…
Anyprefer: An Agentic Framework for Preference Data Synthesis
Yiyang Zhou, Zhaoyang Wang, Tianle Wang +13
High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consum…
Synergistic Weak-Strong Collaboration by Aligning Preferences
Yizhu Jiao, Xuchao Zhang, Zhaoyang Wang +7
Current Large Language Models (LLMs) excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for…
eARCO: Efficient Automated Root Cause Analysis with Prompt Optimization
Drishti Goel, Raghav Magazine, Supriyo Ghosh +5
Root cause analysis (RCA) for incidents in large-scale cloud systems is a complex, knowledge-intensive task that often requires significant manual effort from on-call engineers (OC…
Verifiable Format Control for Large Language Model Generations
Zhaoyang Wang, Jinqi Jiang, Huichi Zhou +4
Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained for…
AMPO: Active Multi-Preference Optimization for Self-play Preference Selection
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +2
Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer t…
REFA: Reference Free Alignment for multi-preference optimization
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +2
To mitigate reward hacking from response verbosity, modern preference optimization methods are increasingly adopting length normalization (e.g., SimPO, ORPO, LN-DPO). While effecti…
Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +3
Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy…
CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
Taneesh Gupta, Shivam Shandilya, Xuchao Zhang +5
Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily…
CREAM: Consistency Regularized Self-Rewarding Language Models
Zhaoyang Wang, Weilei He, Zhiyuan Liang +5
Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations fo…
Building AI Agents for Autonomous Clouds: Challenges and Design Principles
Manish Shetty, Yinfang Chen, Gagan Somashekar +10
The rapid growth in the use of Large Language Models (LLMs) and AI Agents as part of software development and deployment is revolutionizing the information technology landscape. Wh…
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Peng Xia, Ze Chen, Juanxi Tian +21
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the…