18 papers
HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning
Juncheng Diao, Zhicong Lu, Peiguang Li +6
While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-hori…
STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios
Sirui Liang, Bohan Yu, Peiyu Wang +8
Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on s…
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
Zhongyu He, Yuanfan Li, Fei Huang +9
Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at…
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…
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
Nan Jia, Haojin Yang, Xing Ma +6
On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement lea…
AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction
Jiashu Yang, Chi Zhang, Abudukelimu Wuerkaixi +5
Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Ex…
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Ai Jian, Xiaoyun Zhang, Eryu Guo +6
Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hun…
Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws
Jinbo Wang, Binghui Li, Zhanpeng Zhou +5
Batch size scheduling (BSS) plays a critical role in large-scale deep learning training, influencing both optimization dynamics and computational efficiency. Yet, its theoretical f…
Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
Xin Yang, Letian Li, Abudukelimu Wuerkaixi +5
Large language models (LLMs) have demonstrated remarkable and steadily improving performance across a wide range of tasks. However, LLM performance may be highly sensitive to promp…
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
Yangyi Fang, Jiaye Lin, Xiaoliang Fu +6
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation…
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Xiaoliang Fu, Jiaye Lin, Yangyi Fang +7
Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms that are fundamentally misali…
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
Jiaming Zhou, Xuxin Cheng, Shiwan Zhao +5
Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains cost…
Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue
Yuhang Jia, Pei Liu, Haoqin Sun +6
End-to-end Spoken Language Models (SLMs) hold great potential for paralinguistic perception, and numerous studies have aimed to enhance their capabilities, particularly for empathe…
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
Ai Jian, Jingqing Ruan, Xing Ma +5
Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human…
Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Xuxin Cheng, Ke Zeng, Zhiquan Cao +65
Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language…
Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +4
Detecting abnormal events in real-world customer service dialogues is highly challenging due to the complexity of business data and the dynamic nature of customer interactions. Mor…
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
Qi Liu, Jingqing Ruan, Hao Li +7
Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and…
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +6
Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on s…