12 citations · 30 across the 48 of their papers we have counts for
34 papers · 1 filter
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…
OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation
Guibin Zhang, Xun Xu, Yanwei Yue +4
Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store tra…
SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?
Jiamin Chen, Yidi Wu, Qiexiang Wang +6
Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than construct…
DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation
Jiamin Chen, Qianben Chen, Jiawen Zhang +5
Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cros…
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
Qianben Chen, Tianrui Qin, King Zhu +21
Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, gen…
EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
Xavier Hu, Jinxiang Xia, Shengze Xu +13
Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-sp…
O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
Yi Yao, He Zhu, Piaohong Wang +12
The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this…
How Far Are We from Genuinely Useful Deep Research Agents?
Dingling Zhang, He Zhu, Jincheng Ren +15
Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRAs were validated on…
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Piaohong Wang, Motong Tian, Jiaxian Li +8
Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-…
Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
Chenghao Zhu, Meiling Tao, Tiannan Wang +3
Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reach…
AFM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
Qianben Chen, Jingyi Cao, Jiayu Zhang +12
Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, whic…
COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
Yunwen Li, Shuangshuang Ying, Xingwei Qu +16
Large language models exhibit systematic deficiencies in creative writing, particularly in non-English contexts where training data is scarce and lacks process-level supervision. W…
ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
Xin Gui, King Zhu, JinCheng Ren +17
In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling chal…
Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures
Shuangshuang Ying, Yunwen Li, Xingwei Qu +21
Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We intr…
Towards Personalized Deep Research: Benchmarks and Evaluations
Yuan Liang, Jiaxian Li, Yuqing Wang +11
Deep Research Agents (DRAs) can autonomously conduct complex investigations and generate comprehensive reports, demonstrating strong real-world potential. However, existing evaluat…
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
Shilong Li, Xingyuan Bu, Wenjie Wang +22
AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However, existing benchmarks such as BrowseCom…
IFEvalCode: Controlled Code Generation
Jian Yang, Wei Zhang, Shukai Liu +9
Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world appl…
A Survey on Latent Reasoning
Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng +30
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate s…
MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Dongyi Ding, Tiannan Wang, Chenghao Zhu +3
Large language models (LLMs) excel at reasoning tasks requiring long thought sequences for planning, reflection, and refinement. However, their substantial model size and high comp…
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
Xiangru Tang, Tianrui Qin, Tianhao Peng +15
AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumula…
TaskCraft: Automated Generation of Agentic Tasks
Dingfeng Shi, Jingyi Cao, Qianben Chen +14
Agentic tasks, which require multi-step problem solving with autonomy, tool use, and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. However…
PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
Meiling Tao, Chenghao Zhu, Dongyi Ding +3
With the rapid improvement in the general capabilities of LLMs, LLM personalization, i.e., how to build LLM systems that can generate personalized responses or services that are ta…
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
Jiajun Shi, Jian Yang, Jiaheng Liu +26
Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchm…
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
P Team, Xinrun Du, Yifan Yao +94
Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledg…