397 citations · 1.7k across the 82 of their papers we have counts for
87 papers
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
Som Sagar, Shasha Li, Hejie Cui +2
Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each desi…
RPTune: Learned Context Curation for LLM Catalog Search
Chuxuan Hu, Hejie Cui, Norman Huang +3
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primaril…
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
Rishabh Agrawal, Hejie Cui, Shasha Li +2
A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback from com…
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Yuxing Lu, Yicheng Chen, Shanchan Wu +1
Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation o…
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
Anmol Kankariya, Sercan Ö. Arık
While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction. Furtherm…
An Agentic Approach to Metadata Reasoning
Jiani Zhang, Sercan O. Arik, Cosmin Arad +2
As autonomous LLM agents evolve to perform complex analytical tasks that require integrating multiple datasets, the problem of discovering relevant data sources becomes a key bottl…
Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
Bhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual questio…
VISTA: A Test-Time Self-Improving Video Generation Agent
Do Xuan Long, Xingchen Wan, Hootan Nakhost +3
Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful…
CoDA: Agentic Systems for Collaborative Data Visualization
Zichen Chen, Jiefeng Chen, Sercan Ö. Arik +3
Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation f…
ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff +6
Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the lar…
Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
Xingchen Wan, Han Zhou, Ruoxi Sun +4
Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manu…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling
Fei Wang, Xingchen Wan, Ruoxi Sun +2
Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hind…
MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
Jaehyun Nam, Jinsung Yoon, Jiefeng Chen +3
Agents based on large language models (LLMs) for machine learning engineering (MLE) can automatically implement ML models via code generation. However, existing approaches to build…
An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents
Bowen Jin, Jinsung Yoon, Priyanka Kargupta +2
Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, R…
Retrieval Augmented Time Series Forecasting
Sungwon Han, Seungeon Lee, Meeyoung Cha +2
Time series forecasting uses historical data to predict future trends, leveraging the relationships between past observations and available features. In this paper, we propose RAFT…
Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun +5
Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query fo…
LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Bowen Jin, Jinsung Yoon, Zhen Qin +5
Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true…
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Han Zhou, Xingchen Wan, Ruoxi Sun +5
Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts tha…
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
Xingchen Wan, Han Zhou, Ruoxi Sun +3
Recent advances in long-context large language models (LLMs) have led to the emerging paradigm of many-shot in-context learning (ICL), where it is observed that scaling many more d…
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments
Hongjin Su, Ruoxi Sun, Jinsung Yoon +3
Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data anal…
SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling
Jiefeng Chen, Jie Ren, Xinyun Chen +4
Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, e…
Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling
Maximillian Chen, Ruoxi Sun, Sercan Ö. Arık
Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode…
Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
Bowen Jin, Jinsung Yoon, Jiawei Han +1
Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources. The increasing capacity of LLMs to process longer input sequences…