24 papers
Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach
Jiarui Qin, Junjie Huang, Yunjia Xi +5
Agentic capabilities are increasingly important for modern LLMs, yet remain difficult to evaluate during pretraining. Existing approaches typically rely on static trajectory-derive…
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
Junjie Huang, Jiarui Qin, Di Yin +4
Trajectory data is getting more vital for training large language models for boosting the agentic abilities. Unlike the verifiable domains such as coding or mathematics, scaling tr…
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…
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Qingyao Li, Wenxiang Jiao, Shuai Shao +6
Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which skill to…
VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
Kangning Zhang, Yixing Li, Shuai Shao +9
Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token cor…
MMSkills: Towards Multimodal Skills for General Visual Agents
Kangning Zhang, Shuai Shao, Qingyao Li +8
Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable co…
DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
Siyuan Qi, Xinyuan Wang, Yingxuan Yang +5
Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansi…
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Shuai Pan, Yixiang Liu, Jiaye Gao +7
Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-…
Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
Jie Gao, Yongan Yu, Junzhu Su +3
Adaptive learning refers to educational technologies that track learners' learning progress and adapt the instructional process based on individual learners' learning performance.…
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
Jiachen Zhu, Zhuoying Ou, Congmin Zheng +9
Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly trea…
SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
Hao Guan, Lingyue Fu, Shao Zhang +8
As autonomous code agents move toward end-to-end software development, evaluating their practical autonomy becomes critical. Current benchmarks hide friction by testing agents in p…
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
Rong Shan, Te Gao, Hang Zheng +6
The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerabili…
AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
Qingyao Li, Weiwen Liu, Weinan Zhang +2
Recent advancements in Large Language Models (LLMs) have successfully employed search-based strategies to enhance code generation. However, existing methods typically rely on stati…
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
Jiachen Zhu, Lingyu Yang, Rong Shan +6
The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimen…
Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation
Weiming Zhang, Jihong Wang, Jiamu Zhou +9
Large Language Models (LLMs) have empowered autonomous agents to handle complex web navigation tasks. While recent studies integrate tree search to enhance long-horizon reasoning,…
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…
Adaptive Milestone Reward for GUI Agents
Congmin Zheng, Xiaoyun Mo, Xinbei Ma +10
Reinforcement Learning (RL) has emerged as a mainstream paradigm for training Mobile GUI Agents, yet it struggles with the temporal credit assignment problem inherent in long-horiz…
ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
Junjie Huang, Jiarui Qin, Di Yin +4
Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectiona…
LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
Kangning Zhang, Wenxiang Jiao, Kounianhua Du +4
Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipel…
Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering
Kounianhua Du, Jianxing Liu, Kangning Zhang +6
The rapid evolution of large language models (LLMs) has intensified the demand for effective personalization techniques that can adapt model behavior to individual user preferences…
APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training
Jiarui Qin, Yunjia Xi, Junjie Huang +6
With the rapid development of LLM-based agents, there is a growing trend to incorporate agent-specific data into the pre-training stage of LLMs, aiming to better align LLMs with re…
CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
Lingyue Fu, Xin Ding, Linyue Pan +9
Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capabi…
Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation
Lingyue Fu, Bolun Zhang, Hao Guan +7
Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code ag…
CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
Lingyue Fu, Hao Guan, Bolun Zhang +10
The evaluation of Large Language Models (LLMs) for software engineering has shifted towards complex, repository-level tasks. However, existing benchmarks predominantly rely on coar…