11 papers
Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model
Nanbeige Lab, :, Chen Yang +23
We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-agent, and complex tool-use ta…
Local Minima in Quadratic-Penalty Relaxations of Binary Linear Programs
Cheng-Han Huang, Yongliang Sun, Chaoyan Huang +2
Many combinatorial optimization problems admit quadratic unconstrained binary formulations (QUBO) which can often be relaxed to the box and optimized using scalable gradi…
Differentiable Repairability & Mutations for Scalable Combinatorial Optimization
Yongliang Sun, Ismail Alkhouri, Cheng-Han Huang +3
Combinatorial optimization problems such as Maximum Independent Set (MIS) and Maximum Cut (MaxCut) arise across a wide range of applications, yet solving large-scale instances rema…
DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
Junshuo Zhang, Chengrui Huang, Feng Guo +6
Large language model (LLM) agents that follow the sequential "reason-then-act" paradigm have achieved superior performance in many complex tasks.However, these methods suffer from…
HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation
Chengrui Huang, Junshuo Zhang, Zhiyuan Ma +7
Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation i…
KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
Cheng Gao, Cheng Huang, Kangyang Luo +5
Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations. While existing reinforcemen…
TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation
Dongsheng Wang, Shen Gao, Chengrui Huang +3
Next Point-of-Interest (POI) recommendation is a fundamental task in location-based services. While recent advances leverage Large Language Model (LLM) for sequential modeling, exi…
Generative Next POI Recommendation with Semantic ID
Dongsheng Wang, Yuxi Huang, Shen Gao +3
Point-of-interest (POI) recommendation systems aim to predict the next destinations of user based on their preferences and historical check-ins. Existing generative POI recommendat…
TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation
Chengrui Huang, Shen Gao, Zhengliang Shi +2
Existing tool-learning methods usually rely on supervised fine-tuning, they often overlook fine-grained optimization of internal tool call details, leading to limitations in prefer…
What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks
Chengrui Huang, Zhengliang Shi, Yuntao Wen +4
Tool learning methods have enhanced the ability of large language models (LLMs) to interact with real-world applications. Many existing works fine-tune LLMs or design prompts to en…
360REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System
Shen Gao, Hao Li, Chengrui Huang +4
Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to…