14 citations · 53 across the 16 of their papers we have counts for
15 papers · 1 filter
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Jian Xie, Tianhe Lin, Zilu Wang +16
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information.…
The Model Agreed, But Didn't Learn: Diagnosing Surface Compliance in Large Language Models
Xiaojie Gu, Ziying Huang, Weicong Hong +3
Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring…
CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning
Siye Wu, Jian Xie, Yikai Zhang +1
The emergence of large reasoning models demonstrates that scaling inference-time compute significantly enhances performance on complex tasks. However, it often falls into another t…
Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial Games
Yikai Zhang, Ye Rong, Siyu Yuan +3
Existing language agents often encounter difficulties in dynamic adversarial games due to poor strategic reasoning. To mitigate this limitation, a promising approach is to allow ag…
ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code
Jian Xie, Zhendong Chu, Aoxiao Zhong +5
Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitiga…
ARM: Adaptive Reasoning Model
Siye Wu, Jian Xie, Yikai Zhang +4
While large reasoning models demonstrate strong performance on complex tasks, they lack the ability to adjust reasoning token usage based on task difficulty. This often leads to th…
Implicit Reasoning in Transformers is Reasoning through Shortcuts
Tianhe Lin, Jian Xie, Siyu Yuan +1
Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as w…
AAAR-1.0: Assessing AI's Potential to Assist Research
Renze Lou, Hanzi Xu, Sijia Wang +15
Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, a…
From Persona to Personalization: A Survey on Role-Playing Language Agents
Jiangjie Chen, Xintao Wang, Rui Xu +15
Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate a…
How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
Siye Wu, Jian Xie, Jiangjie Chen +3
By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive…
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
Jian Xie, Kai Zhang, Jiangjie Chen +5
Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognit…
Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning
Tinghui Zhu, Kai Zhang, Jian Xie +1
Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoni…
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
Renze Lou, Kai Zhang, Jian Xie +5
In the realm of large language models (LLMs), enhancing instruction-following capability often involves curating expansive training data. This is achieved through two primary schem…
QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search
Jian Xie, Yidan Liang, Jingping Liu +3
In light of the success of the pre-trained language models (PLMs), continual pre-training of generic PLMs has been the paradigm of domain adaption. In this paper, we propose QUERT,…
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
Jian Xie, Kai Zhang, Jiangjie Chen +2
By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limit…