3 citations · 9 across the 26 of their papers we have counts for
29 papers
MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents
Kounianhua Du, Jianxing Liu, Shuai Shao +3
The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a standardized interface. Lea…
Start Classifying: Categorical Critics for LLM Reinforcement Learning
Zhijian Zhou, Long Li, Xuan Zhang +7
Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets. Although scalar MSE is stat…
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
Xuan Zhang, Zhijian Zhou, Lingfeng Qiao +6
Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans wh…
SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents
Shaofei Cai, Yulei Qin, Haojia Lin +10
Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verif…
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Junru Lu, Jiarui Qin, Lingfeng Qiao +35
We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that r…
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Yuchen Shi, Yuzheng Cai, Siqi Cai +15
Existing Large Language Model (LLM) agent frameworks face two significant challenges: high configuration costs and static capabilities. Building a high-quality agent often requires…
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
Bhaktipriya Radharapu, Eshika Saxena, Kenneth Li +3
As LLM-based judges become integral to industry applications, obtaining well-calibrated uncertainty estimates efficiently has become critical for production deployment. However, ex…
LTD-Bench: Evaluating Large Language Models by Letting Them Draw
Liuhao Lin, Ke Li, Zihan Xu +5
Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research--relying on opaque numerical metrics that conceal fundamental limitatio…
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
Yuhang Zhou, Mingrui Zhang, Ke Li +12
Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approac…
Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards
Xuan Zhang, Ruixiao Li, Zhijian Zhou +7
Reinforcement Learning (RL) has become a compelling way to strengthen the multi step reasoning ability of Large Language Models (LLMs). However, prevalent RL paradigms still lean o…
CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent
Haojia Lin, Xiaoyu Tan, Yulei Qin +9
Computer-using agents (CUAs) enable task completion through natural interaction with operating systems and software interfaces. While script-based verifiers are widely adopted for…
Training-Free Group Relative Policy Optimization
Yuzheng Cai, Siqi Cai, Yuchen Shi +10
Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degr…
RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning
Gang Li, Yulei Qin, Xiaoyu Tan +6
Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often lea…
OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search
Bo Lyu, Yu Cui, Tuo Shi +1
Neural architecture search (NAS) is a hard computationally expensive optimization problem with a discrete, vast, and spiky search space. One of the key research efforts dedicated t…
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Yulei Qin, Xiaoyu Tan, Zhengbao He +13
Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundament…
HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
Ke Li, Zheng Yang, Zhongbin Zhou +3
Mixture-of-Experts (MoE) architectures in large language models (LLMs) deliver exceptional performance and reduced inference costs compared to dense LLMs. However, their large para…
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
Yulei Qin, Gang Li, Zongyi Li +6
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, an…
Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration
Yong Wu, Weihang Pan, Ke Li +3
Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mis…
FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
Yuchen Shi, Siqi Cai, Zihan Xu +7
The integration of workflows with large language models (LLMs) enables LLM-based agents to execute predefined procedures, enhancing automation in real-world applications. Tradition…
The ICME 2025 Audio Encoder Capability Challenge
Junbo Zhang, Heinrich Dinkel, Qiong Song +8
This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit…
Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models
Yuncheng Yang, Yulei Qin, Tong Wu +9
The cultivation of expertise for large language models (LLMs) to solve tasks of specific areas often requires special-purpose tuning with calibrated behaviors on the expected stabl…
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models
Yulei Qin, Yuncheng Yang, Pengcheng Guo +7
Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LL…
IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
Yuzhen Mao, Martin Ester, Ke Li
One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space c…