1 citations · 4 across the 43 of their papers we have counts for
47 papers
Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos
Wei Lin
Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation. We argue they are a different kind…
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Shufan Shen, Zhongni Hou, Junshu Sun +5
The strong generalization performance of on-policy post-training paradigms has motivated studies of their parameter update behaviors. However, these studies treat the observed beha…
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Miteto Wei, Xiaohan Wang, Zehao Chen +7
On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefixes wher…
TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
Zihan Lin, Xiaohan Wang, Jie Cao +4
Efficient exploration often remains a central bottleneck in reinforcement learning with verifiable rewards (RLVR). Although temperature control and test-time scaling strategies can…
Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
Yanyu Zhu, Chenheng Zhang, Shaoshen Chen +8
In open-world scenarios with massive and evolving tool repositories, tool-augmented large language models rely on a retriever to surface relevant tools for a given query. Because s…
One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control
Zihan Lin, Xiaohan Wang, Jie Cao +4
Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain perf…
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
Yucan Guo, Xiaohan Wang, Miao Su +8
Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has be…
ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents
Wei Chen, Peilun Zhou, Zhaoyu Hu +8
Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. Reliable evaluation is essent…
Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
Zihao Cheng, Yingyu Shan, Hongru Wang +6
Travel planning agents assist users in generating personalized travel plans by modeling their individual preferences. Existing agents either rely on explicit user instructions or e…
When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
Zihan Lin, Zhenyu Chen, Jiawen Wei +6
Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents. Prevailing agent self-evolution paradigms typically rely on a co…
Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning
Li Wang, Xiaodong Lu, Xiaohan Wang +4
Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can degrade capabilities already pres…
UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
Siyu Xia, Chenheng Zhang, Yanting Wu +8
Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over boundary-agnostic and evolving ta…
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Yingyu Shan, Yuhang Guo, Zihao Cheng +7
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform c…
Are Full Rollouts Necessary for On-Policy Distillation?
Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7
On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…
-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
Yaocheng Zhang, Yuanheng Zhu, Wenyue Chong +7
Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit…
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Zihao Cheng, Hongru Wang, Zeming Liu +6
Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked by the scarcity of high-qua…
AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
Zhenlin Wei, Pu Jian, Yingzhuo Deng +6
The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO…
Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
Li Wang, Xiaohan Wang, Xiaodong Lu +5
Large language models (LLMs) have increasingly leveraged tool invocation to enhance their reasoning capabilities. However, existing approaches typically tightly couple tool invocat…
RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
Wenwen Zeng, Jinhui Zhang, Hao Chen +10
The integration of Large Language Model (LLM) agents is transforming recommender systems from simple query-item matching towards deeply personalized and interactive recommendations…
Accelerating Compound LLM Training Workloads with Maestro
Xiulong Yuan, Hongqing Chen, Jiaxuan Peng +16
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differin…
SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning
Xuan Wang, Yu Ming, Xinhao Zhong +4
Large Language Models (LLMs) are prone to logical hallucinations and stochastic drifts during long-chain reasoning. While Classifier-Free Guidance (CFG) can improve instruction adh…
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
Jingbo Sun, Wenyue Chong, Songjun Tu +7
Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. Howeve…
MemEvolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation
Zihao Cheng, Zeming Liu, Yingyu Shan +7
While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typi…
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
Song Jin, Juntian Zhang, Xun Zhang +6
Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmar…