Cover Image

Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Xuanbo, Zhang, Yingfang, Luo, Hao, Liu, Xiaoteng, Huang, Leo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ROAST: Rollout-based On-distribution Activation Steering Technique
by: Su, Xuanbo, et al.
Published: (2026)

Sell More, Play Less: Benchmarking LLM Realistic Selling Skill
by: Su, Xuanbo, et al.
Published: (2026)

Retrieved In-Context Principles from Previous Mistakes
by: Sun, Hao, et al.
Published: (2024)

Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction
by: Feng, Xuan, et al.
Published: (2024)

In-Context Principle Learning from Mistakes
by: Zhang, Tianjun, et al.
Published: (2024)

DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
by: You, Ziming, et al.
Published: (2025)

Learning-From-Mistakes Prompting for Indigenous Language Translation
by: Liao, You-Cheng, et al.
Published: (2024)

Mem-T: Densifying Rewards for Long-Horizon Memory Agents
by: Yue, Yanwei, et al.
Published: (2026)

Beyond Learning: A Training-Free Alternative to Model Adaptation
by: Yoon, Namkyung, et al.
Published: (2026)

Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
by: Xue, Tianci, et al.
Published: (2026)

Learning From Mistakes Makes LLM Better Reasoner
by: An, Shengnan, et al.
Published: (2023)

Transparent and Coherent Procedural Mistake Detection
by: Storks, Shane, et al.
Published: (2024)

ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters
by: Yuksel, Kamer Ali, et al.
Published: (2025)

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization
by: Cang, Yueyang, et al.
Published: (2026)

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
by: Tian, Xueyun, et al.
Published: (2026)

Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents
by: Liu, Xunzhuo, et al.
Published: (2026)

Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
by: Tong, Yongqi, et al.
Published: (2024)

Batched Low-Rank Adaptation of Foundation Models
by: Wen, Yeming, et al.
Published: (2023)

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
by: Zhang, Shaokun, et al.
Published: (2025)

TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models
by: Zhang, Li, et al.
Published: (2025)

Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues
by: Zhang, Zory, et al.
Published: (2025)

Towards Reward Modeling for AI Tutors in Math Mistake Remediation
by: Petukhova, Kseniia, et al.
Published: (2026)

From Failure to Mastery: Generating Hard Samples for Tool-use Agents
by: Hao, Bingguang, et al.
Published: (2026)

DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
by: Liao, Huanxuan, et al.
Published: (2025)

When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs
by: Kamoi, Ryo, et al.
Published: (2024)

ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
by: Li, Zechen, et al.
Published: (2025)

Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency
by: Birhane, Abeba, et al.
Published: (2024)

ZeroSearch: Incentivize the Search Capability of LLMs without Searching
by: Sun, Hao, et al.
Published: (2025)

Contextualized Data-Wrangling Code Generation in Computational Notebooks
by: Huang, Junjie, et al.
Published: (2024)

ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
by: Xu, Yiming, et al.
Published: (2025)

Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions
by: Tang, Yiming, et al.
Published: (2024)

Unlocking Insights: Semantic Search in Jupyter Notebooks
by: Li, Lan, et al.
Published: (2024)

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
by: Zou, Jiaru, et al.
Published: (2025)

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
by: Agarwal, Rishabh, et al.
Published: (2023)

EmoLoom-2B: Fast Base-Model Screening for Emotion Classification and VAD with Lexicon-Weak Supervision and KV-Off Evaluation
by: Li, Zilin, et al.
Published: (2026)

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures
by: Hu, Yi, et al.
Published: (2026)

When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction
by: Yang, Yuqing, et al.
Published: (2025)

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
by: Su, Junhao, et al.
Published: (2025)

When Are Reactive Notebooks Not Reactive?
by: Zheng, Megan, et al.
Published: (2025)

Scaling Law for Language Models Training Considering Batch Size
by: Shuai, Xian, et al.
Published: (2024)