Imagen de Portada

Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tang, Chenming, Huang, Hsiu-Yuan, Liu, Weijie, Zheng, Junqiang, Yang, Saiyong, Wu, Yunfang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
por: Tang, Chenming, et al.
Publicado: (2025)

Think Outside the Policy: In-Context Steered Policy Optimization
por: Huang, Hsiu-Yuan, et al.
Publicado: (2025)

CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark
por: Zhang, Junzhao, et al.
Publicado: (2026)

Evaluating the Capability of Large-scale Language Models on Chinese Grammatical Error Correction Task
por: Qu, Fanyi, et al.
Publicado: (2023)

Aligning Language Models with Real-time Knowledge Editing
por: Tang, Chenming, et al.
Publicado: (2025)

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing
por: Wu, Zichen, et al.
Publicado: (2025)

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
por: Liang, Kun, et al.
Publicado: (2026)

Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions
por: Tang, Chenming, et al.
Publicado: (2024)

Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction
por: Tang, Chenming, et al.
Publicado: (2024)

SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation
por: Tang, Chenming, et al.
Publicado: (2024)

Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation
por: Tang, Chenming, et al.
Publicado: (2024)

Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction Tasks
por: Cai, Yida, et al.
Publicado: (2024)

Lost in the Passage: Passage-level In-context Learning Does Not Necessarily Need a "Passage"
por: Sun, Hao, et al.
Publicado: (2025)

Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding
por: Wu, Zichen, et al.
Publicado: (2024)

FPT: Feature Prompt Tuning for Few-shot Readability Assessment
por: Wang, Ziyang, et al.
Publicado: (2024)

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
por: Liang, Kun, et al.
Publicado: (2026)

Beyond Demonstrations: Dynamic Vector Construction from Latent Representations
por: Cai, Wang, et al.
Publicado: (2025)

A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice
por: Huang, Hsiu-Yuan, et al.
Publicado: (2024)

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection
por: Huang, Hsiu-Yuan, et al.
Publicado: (2024)

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
por: Xu, Xin, et al.
Publicado: (2026)

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
por: Yang, Wenkai, et al.
Publicado: (2026)

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
por: Yang, Wenkai, et al.
Publicado: (2025)

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding
por: Qu, Fanyi, et al.
Publicado: (2024)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
por: Xu, Xin, et al.
Publicado: (2025)

ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation
por: Yang, Yutong, et al.
Publicado: (2026)

Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning
por: Li, Gengyang, et al.
Publicado: (2026)

Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists
por: Cui, Yue, et al.
Publicado: (2025)

SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation
por: Li, Gengyang, et al.
Publicado: (2026)

ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
por: Li, Gengyang, et al.
Publicado: (2025)

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking
por: Li, Yanhong, et al.
Publicado: (2025)

Composable Cross-prompt Essay Scoring by Merging Models
por: Lee, Sanwoo, et al.
Publicado: (2025)

Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring
por: Lee, Sanwoo, et al.
Publicado: (2024)

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
por: Du, Yuwen, et al.
Publicado: (2026)

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
por: He, Jie, et al.
Publicado: (2025)

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models
por: Liu, Biao, et al.
Publicado: (2024)

LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model
por: Jiang, Haitao, et al.
Publicado: (2023)

Rank-Then-Score: Enhancing Large Language Models for Automated Essay Scoring
por: Cai, Yida, et al.
Publicado: (2025)

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
por: Apertus, Project, et al.
Publicado: (2025)

Instruct Large Language Models to Drive like Humans
por: Zhang, Ruijun, et al.
Publicado: (2024)

StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs
por: Guo, Zhicheng, et al.
Publicado: (2025)