49 citations · 174 across the 32 of their papers we have counts for
35 papers
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Caiqi Zhang, Rujun Han, Zifeng Wang +4
As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened…
Budget-Aware Tool Use Enables Effective Agent Scaling
Tengxiao Liu, Zifeng Wang, Jin Miao +12
Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool…
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Yihe Deng, I-Hung Hsu, Jun Yan +7
Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLV…
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
Siru Ouyang, Jun Yan, I-Hung Hsu +14
With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their f…
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…
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation
Fan Yin, Zifeng Wang, I-Hung Hsu +9
Large language models (LLMs) have exhibited the ability to effectively utilize external tools to address user queries. However, their performance may be limited in complex, multi-t…
STAR: Stability-Inducing Weight Perturbation for Continual Learning
Masih Eskandar, Tooba Imtiaz, Davin Hill +2
Humans can naturally learn new and varying tasks in a sequential manner. Continual learning is a class of learning algorithms that updates its learned model as it sees new data (on…
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
Zhen Tan, Jun Yan, I-Hung Hsu +12
Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limi…
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Mihir Parmar, Xin Liu, Palash Goyal +11
Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complex…
When One LLM Drools, Multi-LLM Collaboration Rules
Shangbin Feng, Wenxuan Ding, Alisa Liu +10
This position paper argues that in many realistic (i.e., complex, contextualized, subjective) scenarios, one LLM is not enough to produce a reliable output. We challenge the status…
Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Shangbin Feng, Zifeng Wang, Palash Goyal +8
We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights. We represent multi-LLM systems as directed acyclic graphs (…
Reverse Thinking Makes LLMs Stronger Reasoners
Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi +8
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towa…
OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
Lichang Chen, Hexiang Hu, Mingda Zhang +8
We introduce OmnixR, an evaluation suite designed to benchmark SoTA Omni-modality Language Models, such as GPT-4o and Gemini. Evaluating OLMs, which integrate multiple modalities s…
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Shangbin Feng, Zifeng Wang, Yike Wang +9
We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms start…
TableRAG: Million-Token Table Understanding with Language Models
Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos +7
Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze…
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li +8
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phe…
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
I-Hung Hsu, Zifeng Wang, Long T. Le +4
Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources. However, existi…
CodecLM: Aligning Language Models with Tailored Synthetic Data
Zifeng Wang, Chun-Liang Li, Vincent Perot +5
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token predic…
Continual Learning of Large Language Models: A Comprehensive Survey
Haizhou Shi, Zihao Xu, Hengyi Wang +6
The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction…
ADAPT to Robustify Prompt Tuning Vision Transformers
Masih Eskandar, Tooba Imtiaz, Zifeng Wang +1
The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks. Many existing defenses against these attacks, such as adversarial t…
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Zilong Wang, Hao Zhang, Chun-Liang Li +8
Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verificat…
LMDX: Language Model-based Document Information Extraction and Localization
Vincent Perot, Kai Kang, Florian Luisier +9
Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, th…
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
Ruoxi Sun, Sercan Ö. Arik, Alex Muzio +8
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially…
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Zifeng Wang, Zheng Zhan, Yifan Gong +4
Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of da…