20 papers
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
Yihao Hu, Zhihao Wen, Yitong Lin +5
Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-step dependencies or contain actions that are unjusti…
Rotochemical heating of neutron stars in 2D
Mikhail V. Beznogov, Jerome Novak, Dany Page +1
The matter inside a spinning-down neutron star (NS) undergoes a slow compression that may drive it out of chemical equilibrium and, consequently, trigger non-equilibrium nuclear re…
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Yongqi Tong, Pan Wang, Hang Wang +4
Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitat…
Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context
Yiwen Zhao, Zhihao Wen, Yuchen Mao +5
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a t…
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
Pan Wang, Yihao Hu, Hang Wang +6
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many…
Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning
Yuting Liu, Wei Wu, Jianzhe Zhao +1
Natural language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain information irrelevant to a part…
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
Chang Liu, Chaoyang Ning, Dayi Jiang +32
Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture int…
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
Yihao Hu, Zhihao Wen, Xiujin Liu +3
Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. W…
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Kaiyi Zhang, Wei Wu, Yankai Lin
Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Despite its effectivenes…
WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
Yu Shang, Yinzhou Tang, Yiding Ma +26
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, ex…
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Han Chen, Zining Zhang, Wenqi Pei +6
Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial…
Text as a Universal Interface for Transferable Personalization
Yuting Liu, Jian Guan, Jia-Nan Li +4
We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yie…
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Jia-Nan Li, Jian Guan, Wei Wu +1
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high…
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
Zhiheng Xi, Chenyang Liao, Guanyu Li +12
Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation,…
Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
Jia-Nan Li, Jian Guan, Wei Wu +1
Large language models (LLMs) have demonstrated significant success in complex reasoning tasks such as math and coding. In contrast to these tasks where deductive reasoning predomin…
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
Chuanqi Cheng, Jian Guan, Wei Wu +1
Long-form video processing fundamentally challenges vision-language models (VLMs) due to the high computational costs of handling extended temporal sequences. Existing token prunin…
A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications
Jian Guan, Junfei Wu, Jia-Nan Li +2
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to ind…
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
Jia-Nan Li, Jian Guan, Songhao Wu +2
Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in…
From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
Chuanqi Cheng, Jian Guan, Wei Wu +1
We explore multi-step reasoning in vision-language models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are b…
"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Chuanqi Cheng, Quan Tu, Shuo Shang +4
Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing…