Image de couverture de livre

Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Yiran, Zhou, Shengyang, Wu, Zijian, Hu, Tongyan, Xu, Yuhui, Dou, Rengan, Kawaguchi, Kenji, Joty, Shafiq, Li, Junnan, Shieh, Michael Qizhe
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
par: Chen, Yuxin, et autres
Publié: (2025)

In-Context Reinforcement Learning for Tool Use in Large Language Models
par: Ye, Yaoqi, et autres
Publié: (2026)

The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift
par: Hong, Zhe
Publié: (2026)

The Boiling-Frog Problem of Physics Education
par: Kortemeyer, Gerd
Publié: (2025)

Unnatural Languages Are Not Bugs but Features for LLMs
par: Duan, Keyu, et autres
Publié: (2025)

NAACL2025 Tutorial: Adaptation of Large Language Models
par: Ke, Zixuan, et autres
Publié: (2025)

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
par: Liu, Xiangyan, et autres
Publié: (2025)

JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
par: Niu, Tong, et autres
Publié: (2024)

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
par: Zhao, Yiran, et autres
Publié: (2026)

Lifelong Event Detection with Embedding Space Separation and Compaction
par: Qin, Chengwei, et autres
Publié: (2024)

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
par: Wu, Zijian, et autres
Publié: (2025)

Reasoning Robustness of LLMs to Adversarial Typographical Errors
par: Gan, Esther, et autres
Publié: (2024)

LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
par: Chen, Guanzheng, et autres
Publié: (2025)

How do Large Language Models Handle Multilingualism?
par: Zhao, Yiran, et autres
Publié: (2024)

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
par: Bisconti, Piercosma, et autres
Publié: (2026)

Training Optimal Large Diffusion Language Models
par: Ni, Jinjie, et autres
Publié: (2025)

On Context Utilization in Summarization with Large Language Models
par: Ravaut, Mathieu, et autres
Publié: (2023)

AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging
par: Zhao, Yiran, et autres
Publié: (2024)

Variation in Verification: Understanding Verification Dynamics in Large Language Models
par: Zhou, Yefan, et autres
Publié: (2025)

Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
par: Li, Xingxuan, et autres
Publié: (2023)

What Makes a Good Natural Language Prompt?
par: Long, Do Xuan, et autres
Publié: (2025)

Evaluating Psychological Safety of Large Language Models
par: Li, Xingxuan, et autres
Publié: (2022)

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
par: Brown, Hannah, et autres
Publié: (2024)

Single Character Perturbations Break LLM Alignment
par: Lin, Leon, et autres
Publié: (2024)

Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
par: Zhao, Yiran, et autres
Publié: (2024)

LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
par: Chen, Guanzheng, et autres
Publié: (2026)

Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction
par: Guo, Ziyao, et autres
Publié: (2025)

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
par: Long, Do Xuan, et autres
Publié: (2025)

Learning from Language Feedback via Variational Policy Distillation
par: Li, Yang, et autres
Publié: (2026)

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models
par: Islam, Shayekh Bin, et autres
Publié: (2024)

Unsupervised Summarization Re-ranking
par: Ravaut, Mathieu, et autres
Publié: (2022)

Diffusion Language Models are Super Data Learners
par: Ni, Jinjie, et autres
Publié: (2025)

It's Not The Plane -- It's The Pilot: A Framework for Cognitive-Activated AI-Augmentation to Avoid the Boiling Frog Problem
par: Kuhn, Jochen, et autres
Publié: (2026)

Harnessing LLM Agents with Skill Programs
par: Liu, Hongjun, et autres
Publié: (2026)

ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
par: Masry, Ahmed, et autres
Publié: (2024)

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
par: Li, Xingxuan, et autres
Publié: (2024)

Exploring Self-supervised Logic-enhanced Training for Large Language Models
par: Jiao, Fangkai, et autres
Publié: (2023)

Investigating Layer Importance in Large Language Models
par: Zhang, Yang, et autres
Publié: (2024)

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing
par: Jiao, Fangkai, et autres
Publié: (2024)

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
par: Li, Xingxuan, et autres
Publié: (2023)