Imagen de Portada

Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Ching-An, Nie, Allen, Swaminathan, Adith
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Importance of Directional Feedback for LLM-based Optimizers
por: Nie, Allen, et al.
Publicado: (2024)

Understanding the Challenges in Iterative Generative Optimization with LLMs
por: Nie, Allen, et al.
Publicado: (2026)

The Context Gathering Decision Process: A POMDP Framework for Agentic Search
por: Kausik, Chinmaya, et al.
Publicado: (2026)

POLCA: Stochastic Generative Optimization with LLM
por: Ren, Xuanfei, et al.
Publicado: (2026)

Provably Learning from Language Feedback
por: Xu, Wanqiao, et al.
Publicado: (2025)

Lost in Transmission: When and Why LLMs Fail to Reason Globally
por: Schnabel, Tobias, et al.
Publicado: (2025)

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
por: Tomlinson, Kiran, et al.
Publicado: (2026)

Differentiating Student Feedbacks for Knowledge Tracing
por: Cui, Jiajun, et al.
Publicado: (2022)

On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
por: Herlihy, Christine, et al.
Publicado: (2024)

Tracing Computation Density in LLMs
por: Kervadec, Corentin, et al.
Publicado: (2026)

Learning Game-Playing Agents with Generative Code Optimization
por: Kuang, Zhiyi, et al.
Publicado: (2025)

What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces
por: Armengol-Estapé, Jordi, et al.
Publicado: (2025)

Combining Open-box Simulation and Importance Sampling for Tuning Large-Scale Recommenders
por: Paneri, Kaushal, et al.
Publicado: (2024)

ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback
por: Zhai, Bohan, et al.
Publicado: (2025)

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
por: Huh, Gio, et al.
Publicado: (2025)

TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
por: Suh, Namjoon, et al.
Publicado: (2024)

DDTR: Diffusion Denoising Trace Recovery
por: Matyash, Maximilian, et al.
Publicado: (2025)

Generative AI-in-the-loop: Integrating LLMs and GPTs into the Next Generation Networks
por: Zhang, Han, et al.
Publicado: (2024)

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
por: Williams, Marcus, et al.
Publicado: (2024)

Deep Reinforcement Learning with Gradient Eligibility Traces
por: Elelimy, Esraa, et al.
Publicado: (2025)

Ray-Tracing for Conditionally Activated Neural Networks
por: Gallicchio, Claudio, et al.
Publicado: (2025)

Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs
por: Hohensinner, Richard, et al.
Publicado: (2026)

Watermarking across Modalities for Content Tracing and Generative AI
por: Fernandez, Pierre
Publicado: (2025)

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
por: Deng, Xinle, et al.
Publicado: (2026)

UrbanMIMOMap: A Ray-Traced MIMO CSI Dataset with Precoding-Aware Maps and Benchmarks
por: Jia, Honggang, et al.
Publicado: (2025)

Generating the Traces You Need: A Conditional Generative Model for Process Mining Data
por: Graziosi, Riccardo, et al.
Publicado: (2024)

Enhancing Knowledge Tracing with Concept Map and Response Disentanglement
por: Park, Soonwook, et al.
Publicado: (2024)

Probing the Trajectories of Reasoning Traces in Large Language Models
por: Ballon, Marthe, et al.
Publicado: (2026)

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
por: Suresh, Praneet, et al.
Publicado: (2025)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
por: Salah, Ahmed, et al.
Publicado: (2025)

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
por: Kim, Donghwan, et al.
Publicado: (2026)

$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation
por: Koh, Woosung, et al.
Publicado: (2024)

Tracing the Heart's Pathways: ECG Representation Learning from a Cardiac Conduction Perspective
por: Pan, Tan, et al.
Publicado: (2025)

EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
por: Nie, Allen, et al.
Publicado: (2024)

AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
por: Wang, Zhaohui Geoffrey
Publicado: (2026)

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding
por: Lv, Yiqin, et al.
Publicado: (2025)

Inverse Deep Learning Ray Tracing for Heliostat Surface Prediction
por: Lewen, Jan, et al.
Publicado: (2024)

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
por: Chowdhury, Sanjoy, et al.
Publicado: (2026)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
por: Dai, Xinnan, et al.
Publicado: (2025)

MemoryKT: An Integrative Memory-and-Forgetting Method for Knowledge Tracing
por: Lin, Mingrong, et al.
Publicado: (2025)