27 papers
EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds
Runxuan Liu, Jingqi Shi, Baoxin Wang +10
Multi-modal agents have made significant progress in interacting with open worlds. However, their ability to self-evolve remains limited. Supervised fine-tuning enables imitation b…
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Linji Hao, Yanji He, Zihan Wang +6
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies acr…
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Hansi Yang, Linji Hao, Hongyan Hao +4
The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces…
Regularity and compactness theory of stable free-boundary minimal hypersurfaces
Costante Bellettini, Martin Man-chun Li, Davide Parise +1
We establish the free-boundary version of Schoen-Simon's regularity and compactness theory for stable minimal hypersurfaces in a complete -dimensional Riemannian manifold-wi…
Consistent Plan-Act for Long-Horizon Agentic Tasks
Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang +4
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning…
FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales
Shidu Ren, Qilin Gu, Zhenghao Ni +4
Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically use fixed-length chunks and e…
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Tianjie Ju, Zheng Wu, Yueqing Sun +15
Multimodal large language models (MLLMs) can interpret a street view, but reliable urban action depends on whether such local evidence remains useful after the agent starts to move…
MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models
Zhekai Wang, Haoxiang Huang, Xiang Liu +6
Object-centric world models forecast future videos by evolving a set of entity slots, but the variables receiving dynamics supervision are often unconstrained visual features. We i…
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Zhiyuan Yao, Yuxin Chen, Zhengxi Lu +13
Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independen…
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
HONOR Agentic Search Team, Zhengzong Chen, Lei Tang +27
We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamenta…
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation
Jinwei Xiao, Zhuowen Han, Yueqing Sun +6
On-policy distillation transfers reasoning ability through dense token-level supervision, yet the nature of the transferable signal remains unclear. We discover that reasoning chai…
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection
Zheng Wu, Chengcheng Han, Zhengxi Lu +5
Despite the rapid progress of multimodal large language models in building Graphical User Interface (GUI) agents, their real-world task completion is fundamentally bottlenecked by…
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Zhengxi Lu, Zhiyuan Yao, Jinyang Wu +7
Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting L…
Self-Distilled Agentic Reinforcement Learning
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8
Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon…
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
Yuxin Liu, Ziang Ye, Yueqing Sun +6
Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforeh…
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Yaorui Shi, Yuxin Chen, Zhengxi Lu +6
A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selec…
MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
Tianjie Ju, Yueqing Sun, Zheng Wu +7
Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic op…
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation
Wentao Shi, Yu Wang, Yuyang Zhao +8
As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly c…
: Generalist Value Model as a Prior for Sparse RL Rollouts
Yi-Kai Zhang, Yueqing Sun, Hongyan Hao +4
In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinfor…
TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training
Jinluan Yang, Yuxin Liu, Zhengyu Chen +7
Training tool-use agents typically relies on outcome-based filtering: Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected…
AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
Ruipeng Wang, Yuxin Chen, Yukai Wang +9
Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployment…
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Yaorui Shi, Shugui Liu, Yu Yang +7
Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as t…