2 citations · 5 across the 13 of their papers we have counts for
14 papers
Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests
Tianyu Chen, Yasi Zhang, Ruiyi Wang +3
Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In…
Efficient Test-Time Adaptation through Human-AI Interaction
Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao +22
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar profes…
AgentSociety 2: An Integrated Research Environment for Executable Social Science
Jinghua Piao, Jun Zhang, Haoyu Huang +16
AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or labora…
Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation
Chenyang Yang, Xinran Zhao, Tongshuang Wu +1
Frontier LLM agents are automating many business tasks, but their high inference cost makes large-scale deployment unsustainable. Small language models (SLMs) offer a cheaper alter…
Improving Attributed Long-form Question Answering with Intent Awareness
Xinran Zhao, Aakanksha Naik, Jay DeYoung +4
Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers…
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Rulin Shao, Akari Asai, Shannon Zejiang Shen +18
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form…
The Ramon Llull's Thinking Machine for Automated Ideation
Xinran Zhao, Boyuan Zheng, Chenglei Si +8
This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern…
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree
Yilin Zhang, Xinran Zhao, Zora Zhiruo Wang +3
Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical…
RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems
Yixiao Zeng, Tianyu Cao, Danqing Wang +5
Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, confli…
Improving Large Language Model Planning with Action Sequence Similarity
Xinran Zhao, Hanie Sedghi, Bernd Bohnet +2
Planning is essential for artificial intelligence systems to look ahead and proactively determine a course of actions to reach objectives in the virtual and real world. Recent work…
Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
Danqing Wang, Zhuorui Ye, Xinran Zhao +2
Winning competitive debates requires sophisticated reasoning and argument skills. There are unique challenges in the competitive debate: (1) The time constraints force debaters to…
SPHERE: An Evaluation Card for Human-AI Systems
Qianou Ma, Dora Zhao, Xinran Zhao +6
In the era of Large Language Models (LLMs), establishing effective evaluation methods and standards for diverse human-AI interaction systems is increasingly challenging. To encoura…
HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation
Zirui Wang, Xinran Zhao, Simon Stepputtis +4
Understanding and predicting human actions has been a long-standing challenge and is a crucial measure of perception in robotics AI. While significant progress has been made in ant…
"Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs
Cheng Qian, Xinran Zhao, Sherry Tongshuang Wu
Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. However, in order to remain up-to-date and align with human instr…