10 papers
Agent-G: Gaussian Guidance for Agentic Reinforcement Learning
Zixuan Wang, Yanrui Miao, Zhengxi Lu +6
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rollout, letting the policy expl…
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Hongxing Li, Xiufeng Huang, Dingming Li +11
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approach…
T-Mem: Memory That Anticipates, Not Archives
Weidong Guo, Dakai Wang, Zixuan Wang +2
Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their beha…
Milestone-Guided Policy Learning for Long-Horizon Language Agents
Zixuan Wang, Yuchen Yan, Hongxing Li +7
While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identif…
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Dinging Li, Yingxiu Zhao, Xinrui Cheng +16
Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annot…
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
Teng Pan, Yuchen Yan, Zixuan Wang +6
Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as…
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Hongxing Li, Dingming Li, Zixuan Wang +7
Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We id…
GroundAct: Can LLM Agents Ground Actions in Environmental States?
Zixuan Wang, Dingming Li, Hongxing Li +8
LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instructi…
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
Dingming Li, Hongxing Li, Zixuan Wang +9
Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring c…