21 papers
From Outcomes to Steps: Reliable Success-Aware Critic Learning for Long-Horizon Language Agents
Jiaxi Liu, Shixiong Kai, Zhentao Tang +4
Reinforcement learning for long-horizon language agents requires identifying whether intermediate actions make eventual task success more or less likely when supervision is availab…
Test-time Calibration Learning for Large Language Model Reasoning
Zizhuo Zhang, Xiong Peng, Jingwei Sun +4
Reliable large language models (LLMs) must not only produce accurate answers but also express confidence that faithfully reflects their probability of being correct. Such calibrati…
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting
Guanyu Nie, Fangzhou Zhu, Shixiong Kai +3
Language-model agents increasingly improve by converting execution experience into reusable external skills. Yet repeated skill updates form a learning process of their own: locall…
MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents
Kaichao Liang, Yuqi Cui, Hao Kong +13
Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems o…
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
Qingcan Kang, Mingyang Liu, Shixiong Kai +5
Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can b…
Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents
Qingcan Kang, Liu Mingyang, Shixiong Kai +3
Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation pro…
EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
Qingcan Kang, Mingyang Liu, Xiaojin Fu +3
Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data g…
ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information
Zehua Liu, Yuxuan Yao, Xiaojin Fu +2
Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce di…
From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting
Mingyang Liu, Qingcan Kang, Yuke Wang +6
Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-base…
Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
Haoyang Liu, Jie Wang, Boxuan Niu +8
Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language m…
RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning
Zehua Liu, Shuqi Liu, Tao Zhong +1
While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samp…
Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
Bowei He, Lihao Yin, Huiling Zhen +5
Post-training compression has been a widely employed approach to scale down large language model (LLM) and facilitate efficient inference. In various proposed compression methods,…
REG: A Regularization Optimizer for Robust Training Dynamics
Zehua Liu, Han Wu, Xiaojin Fu +4
Optimizers are crucial for the efficient training of Large Language Models (LLMs). While AdamW is the de facto standard, recent structure-aware optimizers like Muon have emerged, w…
SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
Yansen Zhang, Qingcan Kang, Yujie Chen +5
Large language models (LLMs) have opened new paradigms in optimization modeling by enabling the generation of executable solver code from natural language descriptions. Despite thi…
A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions
Ziyang Xiao, Jingrong Xie, Lilin Xu +15
By virtue of its great utility in solving real-world problems, optimization modeling has been widely employed for optimal decision-making across various sectors, but it requires su…
MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models
Zehua Liu, Han Wu, Ruifeng She +4
Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each inpu…
Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging
Han Wu, Yuxuan Yao, Shuqi Liu +7
The transition from System 1 to System 2 reasoning in large language models (LLMs) has marked significant advancements in handling complex tasks through deliberate, iterative think…
Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
Shuqi Liu, Han Wu, Bowei He +3
Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized…
ARS: Automatic Routing Solver with Large Language Models
Kai Li, Fei Liu, Zhenkun Wang +4
Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming. Althoug…
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
Zehua Liu, Han Wu, Yuxuan Yao +4
While most current approaches rely on further training techniques, such as fine-tuning or reinforcement learning, to enhance model capacities, model merging stands out for its abil…
1bit-Merging: Dynamic Quantized Merging for Large Language Models
Shuqi Liu, Yuxuan Yao, Bowei He +5
Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional mer…