34 citations · 97 across the 36 of their papers we have counts for
37 papers
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Xingshan Zeng, Zishan Xu, Boju Zhang +11
LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments…
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Zishan Xu, Zhiyuan Yao, Yuxin Chen +9
Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verificatio…
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
Ning Li, Zixuan Guo, Yan Xu +7
Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided…
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
Haoyi Hu, Qirong Lyu, Xianghan Kong +7
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This par…
LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
Jizheng Chen, Weiming Zhang, Xinyi Dai +6
Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured tree search, have made pro…
ATGen: Adversarial Reinforcement Learning for Test Case Generation
Qingyao Li, Xinyi Dai, Weiwen Liu +5
Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generati…
ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
Xingshan Zeng, Weiwen Liu, Lingzhi Wang +6
Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existi…
Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
Xinda Jia, Jinpeng Li, Zezhong Wang +6
Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains. However, effective reasoning in real-world tasks requires adapting the reaso…
Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
Xiangyang Li, Xiaopeng Li, Kuicai Dong +7
Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and po…
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
Hanting Chen, Jiarui Qin, Jialong Guo +15
Large Language Models (LLMs) deliver state-of-the-art capabilities across numerous tasks, but their immense size and inference costs pose significant computational challenges for p…
InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
Yunjia Xi, Jianghao Lin, Menghui Zhu +10
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances…
ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
Xu Huang, Weiwen Liu, Xingshan Zeng +8
The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capa…
Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
Yehui Tang, Yichun Yin, Yaoyuan Wang +71
Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models. However, the massive…
Advancing and Benchmarking Personalized Tool Invocation for LLMs
Xu Huang, Yuefeng Huang, Weiwen Liu +5
Tool invocation is a crucial mechanism for extending the capabilities of Large Language Models (LLMs) and has recently garnered significant attention. It enables LLMs to solve comp…
Position: The Real Barrier to LLM Agent Usability is Agentic ROI
Weiwen Liu, Jiarui Qin, Xu Huang +10
Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, plan…
Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
Kuicai Dong, Yujing Chang, Shijie Huang +3
Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current do…
NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
Weiming Zhang, Qingyao Li, Xinyi Dai +7
Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programmin…
Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs
Yichun Yin, Wenyong Huang, Kaikai Song +49
We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field…
AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing
Lingyue Fu, Ting Long, Jianghao Lin +6
Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences. Existing KT models typically follow a single-step training paradigm,…
ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
Xingshan Zeng, Weiwen Liu, Xu Huang +8
Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabiliti…
Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
Kounianhua Du, Hanjing Wang, Jianxing Liu +7
Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms i…
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
Wenjun Li, Dexun Li, Kuicai Dong +6
Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that requ…
A Survey on Multi-Turn Interaction Capabilities of Large Language Models
Chen Zhang, Xinyi Dai, Yaxiong Wu +4
Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and context…
ACEBench: Who Wins the Match Point in Tool Usage?
Chen Chen, Xinlong Hao, Weiwen Liu +13
Large Language Models (LLMs) have demonstrated significant potential in decision-making and reasoning, particularly when integrated with various tools to effectively solve complex…