16 citations · 54 across the 56 of their papers we have counts for
61 papers
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Zongxia Li, Zhongzhi Li, Yucheng Shi +14
Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary che…
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Zongxia Li, Yucheng Shi, Zhongzhi Li +7
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during depl…
Self-Supervised Scaling of Terminal Environments for Scientific Domains
Zhongzhi Li, Yucheng Shi, Zongxia Li +8
Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference beh…
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Junyao Yang, Yucheng Shi, Zhongzhi Li +4
Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks are especially important. We introduce T1, a Mixture-of-Expert…
Recursive Synthesis for Long-Horizon Terminal Tasks
Zhongzhi Li, Yucheng Shi, Zongxia Li +8
High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instru…
Self-Evolving Code-with-Image Reasoning
Tianze Yang, Liang Wu, Ruitong Sun +6
Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of p…
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Junyao Yang, Yucheng Shi, Zongxia Li +6
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but the resulting staleness is an inevitable byproduct, compounded joint…
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…
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Ruhan Wang, Yucheng Shi, Zongxia Li +7
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execut…
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi +12
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minu…
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11
Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive…
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding
Jingyuan Huang, Zuming Huang, Yucheng Shi +4
Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordina…
Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning
Jiangnan Xia, Yucheng Shi, Yu Yang +3
Reinforcement learning has become a key paradigm for eliciting reasoning abilities in large language models, where exploration is crucial for discovering effective solution traject…
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Jiaxi Li, Ke Deng, Yun Wang +5
Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill learning, where agents c…
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning
Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang +1
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language c…
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi +1
Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands con…
Self-Improving Small Object Grounding in LVLMs
Tianze Yang, Yucheng Shi, Ruitong Sun +2
Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning? In this work, we provide an affirmative answer. At…
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Tianze Yang, Yucheng Shi, Ruitong Sun +3
Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets,…
Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning
Jun-Tao Tang, Yu-Cheng Shi, Zhen-Hao Xie +1
Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-wor…
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Yucheng Shi, Zhenwen Liang, Kishan Panaganti +3
We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In z…
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
Rui Liu, Dian Yu, Zhenwen Liang +6
Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over…
Reinforcing Multimodal Reasoning Against Visual Degradation
Rui Liu, Dian Yu, Haolin Liu +6
Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-wor…
From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation at Industry Scale
Yucheng Shi, Ying Li, Yu Wang +8
Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user…
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
Zhen-Hao Xie, Jun-Tao Tang, Yu-Cheng Shi +3
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, ma…