Copertina

The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lu, Qingyu, Ding, Liang, Zhang, Kanjian, Zhang, Jinxia, Tao, Dacheng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators
di: Lu, Qingyu, et al.
Pubblicazione: (2024)

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
di: Lu, Qingyu, et al.
Pubblicazione: (2025)

Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models
di: Lu, Qingyu, et al.
Pubblicazione: (2023)

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks
di: Wu, Minghao, et al.
Pubblicazione: (2025)

Intention Analysis Makes LLMs A Good Jailbreak Defender
di: Zhang, Yuqi, et al.
Pubblicazione: (2024)

A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems
di: Amonkar, Rikhil, et al.
Pubblicazione: (2025)

JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models
di: Chen, Michael K., et al.
Pubblicazione: (2025)

Uncertainty Aware Learning for Language Model Alignment
di: Wang, Yikun, et al.
Pubblicazione: (2024)

Revisiting Catastrophic Forgetting in Large Language Model Tuning
di: Li, Hongyu, et al.
Pubblicazione: (2024)

Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation
di: Cai, Shizhan, et al.
Pubblicazione: (2025)

Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
di: Rao, Jun, et al.
Pubblicazione: (2024)

ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
di: Zhong, Qihuang, et al.
Pubblicazione: (2024)

Revisiting Knowledge Distillation for Autoregressive Language Models
di: Zhong, Qihuang, et al.
Pubblicazione: (2024)

A Survey on Agentic Multimodal Large Language Models
di: Yao, Huanjin, et al.
Pubblicazione: (2025)

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
di: Wang, Shuai, et al.
Pubblicazione: (2024)

LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
di: Zhang, Kaichen, et al.
Pubblicazione: (2024)

E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
di: Zhong, Qihuang, et al.
Pubblicazione: (2022)

GNNs as Predictors of Agentic Workflow Performances
di: Zhang, Yuanshuo, et al.
Pubblicazione: (2025)

Learning the Bitter Lesson: Empirical Evidence from 20 Years of CVPR Proceedings
di: Yousefi, Mojtaba, et al.
Pubblicazione: (2024)

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL
di: Zhong, Qihuang, et al.
Pubblicazione: (2024)

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
di: Zhong, Qihuang, et al.
Pubblicazione: (2022)

Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
di: Chen, Kunfeng, et al.
Pubblicazione: (2026)

Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
di: Wu, Yuchen, et al.
Pubblicazione: (2025)

Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
di: Wu, Yuchen, et al.
Pubblicazione: (2025)

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
di: Ho, Zheng Yi, et al.
Pubblicazione: (2024)

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
di: Wu, Yuchen, et al.
Pubblicazione: (2025)

Taxonomy-based CheckList for Large Language Model Evaluation
di: Zhang, Damin
Pubblicazione: (2023)

Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking
di: Lin, Hongzhan, et al.
Pubblicazione: (2026)

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
di: Liu, Boan, et al.
Pubblicazione: (2023)

DyFlow: Dynamic Workflow Framework for Agentic Reasoning
di: Wang, Yanbo, et al.
Pubblicazione: (2025)

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
di: Zhong, Qihuang, et al.
Pubblicazione: (2026)

Temporal Generalization: A Reality Check
di: Madaan, Divyam, et al.
Pubblicazione: (2025)

Self-Powered LLM Modality Expansion for Large Speech-Text Models
di: Yu, Tengfei, et al.
Pubblicazione: (2024)

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
di: Xiao, Yisong, et al.
Pubblicazione: (2025)

Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
di: Zhang, Meicong, et al.
Pubblicazione: (2025)

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models
di: Nie, Ying, et al.
Pubblicazione: (2024)

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning
di: Zhang, Yanfang, et al.
Pubblicazione: (2024)

Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning
di: Zan, Changtong, et al.
Pubblicazione: (2024)

Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
di: Bao, Rong, et al.
Pubblicazione: (2024)

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
di: Peng, Keqin, et al.
Pubblicazione: (2025)