14 papers
From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models
Shuo Cai, Yanggan Gu, Zihao Wang +8
Model fusion integrates the capabilities from source models into a single target model. As of June 2026, Hugging Face hosts more than 2M models. This growing pool provides a rich b…
Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System
Ming Li, Dai Li, Xuying Ning +10
Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this paradigm to industry-scale re…
Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
Chenglin Yu, Li Yin, Qingxin Fan +3
Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP constraints into executable pseudo-co…
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation
Chenglin Yu, Hongquan Gui, Ying Yu +2
LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoin…
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang +3
Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-…
Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
Zhiyuan Zhai, Bingcong Li, Bingnan Xiao +2
Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improvi…
InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation
Yifan Yang, Jinjia Li, Kunxi Li +7
The rapid advancement of large language models (LLMs) demands increasingly reliable evaluation, yet current centralized evaluation suffers from opacity, overfitting, and hardware-i…
Canonical Intermediate Representation for LLM-based optimization problem formulation and code generation
Zhongyuan Lyu, Shuoyu Hu, Lujie Liu +2
Automatically formulating optimization models from natural language descriptions is a growing focus in operations research, yet current LLM-based approaches struggle with the compo…
ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
Xiaoce Wang, Guibin Zhang, Junzhe Li +3
Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce co…
InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents
Chenglin Yu, Yuchen Wang, Songmiao Wang +2
LLM agents can reason and use tools, but they often break down on long-horizon tasks due to unbounded context growth and accumulated errors. Common remedies such as context compres…
InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios
Chenglin Yu, Yang Yu, Songmiao Wang +5
Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various applicati…
A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models
Wenjun Wang, Shuo Cai, Congkai Xie +7
The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theo…
InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning
Zeyu Liu, Zhitian Hou, Guanghao Zhu +3
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in domains such as visual understanding and mathematical reasoning. However, their application in the med…
Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
Zhen Li, Yupeng Su, Songmiao Wang +8
Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reaso…