Cover Image

Decocted Experience Improves Test-Time Inference in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Maohao, Zha, Kaiwen, He, Zexue, Hong, Zhang-Wei, Ouyang, Siru, Ryu, J. Jon, Sattigeri, Prasanna, Diggavi, Suhas, Wornell, Gregory
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
by: Shen, Maohao, et al.
Published: (2024)

Thermometer: Towards Universal Calibration for Large Language Models
by: Shen, Maohao, et al.
Published: (2024)

Gambling-Based Confidence Sequences for Bounded Random Vectors
by: Ryu, J. Jon, et al.
Published: (2024)

Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions
by: Jayashankar, Tejas, et al.
Published: (2025)

A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
by: Ryu, J. Jon, et al.
Published: (2024)

Revisiting Orbital Minimization Method for Neural Operator Decomposition
by: Ryu, J. Jon, et al.
Published: (2025)

Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering
by: Zeng, Guangtao, et al.
Published: (2025)

ICQuant: Index Coding enables Low-bit LLM Quantization
by: Li, Xinlin, et al.
Published: (2025)

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
by: Zha, Kaiwen, et al.
Published: (2025)

Contrastive Predictive Coding Done Right for Mutual Information Estimation
by: Ryu, J. Jon, et al.
Published: (2025)

An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
by: Zhou, Ruida, et al.
Published: (2024)

SPIRE: Conditional Personalization for Federated Diffusion Generative Models
by: Ozkara, Kaan, et al.
Published: (2025)

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
by: Shen, Maohao, et al.
Published: (2025)

Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
by: Jeong, Minchan, et al.
Published: (2025)

Reframing Data Value for Large Language Models Through the Lens of Plausibility
by: Rammal, Mohamad Rida, et al.
Published: (2024)

Robust Federated Personalised Mean Estimation for the Gaussian Mixture Model
by: Managoli, Malhar A., et al.
Published: (2025)

Common Information Dimension
by: Hanna, Osama, et al.
Published: (2023)

ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning
by: Ozkara, Kaan, et al.
Published: (2024)

SkillOS: Learning Skill Curation for Self-Evolving Agents
by: Ouyang, Siru, et al.
Published: (2026)

On the optimal regret of collaborative personalized linear bandits
by: Huang, Bruce, et al.
Published: (2025)

Extremum Encoding for Joint Baseband Signal Compression and Time-Delay Estimation for Distributed Systems
by: Weiss, Amir, et al.
Published: (2024)

A Joint Data Compression and Time-Delay Estimation Method For Distributed Systems via Extremum Encoding
by: Weiss, Amir, et al.
Published: (2024)

Operator SVD with Neural Networks via Nested Low-Rank Approximation
by: Ryu, J. Jon, et al.
Published: (2024)

FlowCompile: An Optimizing Compiler for Structured LLM Workflows
by: Li, Junyan, et al.
Published: (2026)

ProxyThinker: Test-Time Guidance through Small Visual Reasoners
by: Xiao, Zilin, et al.
Published: (2025)

Self-Improving LLM Agents at Test-Time
by: Acikgoz, Emre Can, et al.
Published: (2025)

When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
by: Nagireddy, Manish, et al.
Published: (2024)

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
by: Asif, Sadia, et al.
Published: (2026)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
by: Seshadri, Amrit Diggavi
Published: (2025)

Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction
by: Seshadri, Amrit Diggavi
Published: (2024)

Tracking without Seeing: Geospatial Inference using Encrypted Traffic from Distributed Nodes
by: Yetim, Sadik Yagiz, et al.
Published: (2026)

VCA: Video Curious Agent for Long Video Understanding
by: Yang, Zeyuan, et al.
Published: (2024)

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
by: Liu, Yepeng, et al.
Published: (2025)

GSRM: Generative Speech Reward Model for Speech RLHF
by: Shen, Maohao, et al.
Published: (2026)

Extending Beacon to Hindi: Cultural Adaptation Drives Cross-Lingual Sycophancy
by: Sattigeri, Sarthak
Published: (2026)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
by: Gourabathina, Abinitha, et al.
Published: (2026)

Large Language Model Confidence Estimation via Black-Box Access
by: Pedapati, Tejaswini, et al.
Published: (2024)

Graph-based Uncertainty Metrics for Long-form Language Model Outputs
by: Jiang, Mingjian, et al.
Published: (2024)

DTMamba : Dual Twin Mamba for Time Series Forecasting
by: Wu, Zexue, et al.
Published: (2024)

MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
by: He, Zexue, et al.
Published: (2026)