4 citations · 16 across the 48 of their papers we have counts for
37 papers · 1 filter
Constitutional Midtraining: Content Presence Drives Alignment Gains
Desiree Cho, Cameron Tice, Bernie Hogan +4
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when c…
LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis
Chenhao Yuan, Yinhao Xu, Shuwen Xu +8
Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs), yet existing approaches sha…
MemTools: A Unified Research Framework for Interoperable Agent Memory
Chengfeng Zhao, Jinhui Chen, Sirui Liang +4
While memory systems are essential for agent architectures, pervasive architectural fragmentation restricts systematic research. Existing implementations typically couple different…
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
Chengfeng Zhao, Yuqiao Tan, Shizhu He +3
While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interact…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Tianyi Men, Zhuoran Jin, Pengfei Cao +3
Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While s…
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Yupu Hao, Zhuoran Jin, Huanxuan Liao +2
Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities. Howeve…
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
Zhuoran Jin, Kejian Zhu, Hongbang Yuan +5
Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness i…
SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models
Shiqiang Cai, Nianhong Niu, Shizhu He +2
Scientific literature is expanding at an unprecedented pace, making it increasingly challenging to efficiently organize and access domain knowledge. A high-quality scientific taxon…
GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
Shuwen Xu, Yao Xu, Jiaxiang Liu +4
Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reason…
WideSeek: Advancing Wide Research via Multi-Agent Scaling
Ziyang Huang, Haolin Ren, Xiaowei Yuan +6
Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in par…
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
Huanxuan Liao, Yixing Xu, Shizhu He +6
Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention com…
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Fangyu Lei, Jinxiang Meng, Yiming Huang +5
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with nu…
Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
Yao Xu, Mingyu Xu, Fangyu Lei +7
Recently, models such as OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable performance on complex reasoning tasks through Long Chain-of-Thought (Long-CoT) reasoning. Although…
Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention
Huanxuan Liao, Wen Hu, Yao Xu +3
Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context com…
Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
Yuqiao Tan, Shizhu He, Kang Liu +1
Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a k…
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
Yuqiao Tan, Shizhu He, Huanxuan Liao +2
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it…
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Jianwen Luo, Yiming Huang, Jinxiang Meng +7
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-ta…
Does RAG Really Perform Bad For Long-Context Processing?
Kun Luo, Zheng Liu, Peitian Zhang +3
The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strat…
Towards Adaptive Mechanism Activation in Language Agent
Ziyang Huang, Jun Zhao, Kang Liu
Language Agent could be endowed with different mechanisms for autonomous task accomplishment. Current agents typically rely on fixed mechanisms or a set of mechanisms activated in…
LLaSA: Large Language and Structured Data Assistant
Yao Xu, Shizhu He, Jiabei Chen +5
Structured data, such as tables, graphs, and databases, play a critical role in plentiful NLP tasks such as question answering and dialogue system. Recently, inspired by Vision-Lan…
CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance
Yupu Hao, Pengfei Cao, Zhuoran Jin +4
Tool learning enables the Large Language Models (LLMs) to interact with the external environment by invoking tools, enriching the accuracy and capability scope of LLMs. However, pr…
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
Huanxuan Liao, Shizhu He, Yao Xu +3
In this paper, we propose ural-mbolic ollaborative istillation (), a novel knowledge distillation method for lear…
: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
Huanxuan Liao, Shizhu He, Yupu Hao +4
Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using…
Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
Wangtao Sun, Chenxiang Zhang, XueYou Zhang +7
Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and i…