13 citations · 53 across the 57 of their papers we have counts for
29 papers · 1 filter
Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards
Zhipeng Chen, Wayne Xin Zhao, Ji-Rong Wen
Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers used remain largely inherited…
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through compl…
Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning
Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao +2
Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount…
Computer Environments Elicit General Agentic Intelligence in LLMs
Daixuan Cheng, Shaohan Huang, Yuxian Gu +6
Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers…
From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR
Jia Deng, Jie Chen, Zhipeng Chen +7
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditiona…
Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning
Jia Deng, Jie Chen, Zhipeng Chen +2
Recently, reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs). A core challenge in RLVR…
Towards Effective Code-Integrated Reasoning
Fei Bai, Yingqian Min, Beichen Zhang +6
In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire thi…
MMATH: A Multilingual Benchmark for Mathematical Reasoning
Wenyang Luo, Wayne Xin Zhao, Jing Sha +2
The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex rea…
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
Huatong Song, Jinhao Jiang, Wenqing Tian +7
Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-Augmented Generation (RAG) helps by injecting external information, but cur…
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
Shuang Sun, Huatong Song, Yuhao Wang +10
Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information re…
Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
Zikang Liu, Kun Zhou, Wayne Xin Zhao +3
Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success,…
DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao +1
Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs)…
Neuron-based Personality Trait Induction in Large Language Models
Jia Deng, Tianyi Tang, Yanbin Yin +3
Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-p…
Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
Zhipeng Chen, Kun Zhou, Liang Song +4
Multi-lingual ability transfer has become increasingly important for the broad application of large language models (LLMs). Existing work highly relies on training with the multi-l…
Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
Jinhao Jiang, Junyi Li, Wayne Xin Zhao +3
Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-tr…
Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models
Jie Chen, Yupeng Zhang, Bingning Wang +3
Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic…
Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector
Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao +5
Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we pr…
Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment
Zhipeng Chen, Kun Zhou, Wayne Xin Zhao +2
Large language models (LLMs) are still struggling in aligning with human preference in complex tasks and scenarios. They are prone to overfit into the unexpected patterns or superf…
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Kun Zhou, Beichen Zhang, Jiapeng Wang +6
Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale…
Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao +3
Key-value~(KV) caching is an important technique to accelerate the inference of large language models~(LLMs), but incurs significant memory overhead. To compress the size of KV cac…
Exploring Context Window of Large Language Models via Decomposed Positional Vectors
Zican Dong, Junyi Li, Xin Men +5
Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of t…
Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models
Yushuo Chen, Tianyi Tang, Erge Xiang +5
In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide…
ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao +1
Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning task…
KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
Jinhao Jiang, Kun Zhou, Wayne Xin Zhao +4
In this paper, we aim to improve the reasoning ability of large language models (LLMs) over knowledge graphs (KGs) to answer complex questions. Inspired by existing methods that de…