12 papers
UniJev: Separating Accuracy from Calibration in Trimodal System One Decision Models
Jianing Wang, Youwen Jian, Derong Wang +5
System One models produce probabilistic judgments that software can consume directly, making reliable confidence as important as answer accuracy. Yet joint training across text, im…
VideoJev: System One Model for Video Understanding and Interaction
Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15
Visual agents must turn video observations into timely decisions to track progress and choose what to do next. Building on the emerging System One paradigm, we introduce VideoJev,…
SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design
Jianing Wang, Xintao Wang, Aili Chen +7
Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to bui…
FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models
Yalun Wu, Junfeng Fang, Jiawei Wang +6
Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close…
EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
Chao Fei, Qingyi Si, Kaihua Liang +3
Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent sam…
A Self-Evolving Agent for Longitudinal Personal Health Management
Haoran Li, Jiebi Deng, Tong Jin +10
Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an open-source agent architecture…
FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents
Yue Pan, Ziheng Zhang, Junxiang Lei +3
Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports. This workflow creates a planning-laye…
Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models
Huiyuan Zheng, Houtao Zhang, Boyang Wang +2
Current evaluations for Multimodal Large Language Models (MLLMs) overwhelmingly focus on utility-driven objectives, leaving model behavior under logic-neutral scenarios largely und…
GUI Agents for Continual Game Generation
Yixu Huang, Bo Li, Na Li +8
Generating a game is not the same as making one playable. Existing code-generation approaches often translate a prompt directly into an artifact, leaving interaction-level failures…
When Agents Evolve, Institutions Follow
Chao Fei, Hongcheng Guo, Yanghua Xiao
Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individua…
IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
Haonan Song, Qingchen Xie, Huan Zhu +12
Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (…
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
Ziheng Li, Liu Kang, Feng Xiao +7
Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-graine…