![[2606.03217] An Asymptotic Theory of Chain-of-Thought in In-Context Learning](/static/img/curated/desks/afbytes-tech.png)
[2606.03217] An Asymptotic Theory of Chain-of-Thought in In-Context Learning
Abstract page for arXiv paper 2606.03217: An Asymptotic Theory of Chain-of-Thought in In-Context Learning
America Forever Bytes
llms · AFBytes
Technology
llms
Recent coverage
[2606.03761] Framing Migration News with LLMs: Structured CoT as a Support for Human Interpretation
Abstract page for arXiv paper 2606.03761: Framing Migration News with LLMs: Structured CoT as a Support for Human Interpretation
[2606.01850] Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
Abstract page for arXiv paper 2606.01850: Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
[2605.30711] SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs
Abstract page for arXiv paper 2605.30711: SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs
[2510.14365] Understanding the Ability of LLMs to Handle Character-Level Perturbation
Abstract page for arXiv paper 2510.14365: Understanding the Ability of LLMs to Handle Character-Level Perturbation
[2602.02103] How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
Abstract page for arXiv paper 2602.02103: How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
[2605.28823] What are They Thinking? Delineation, Probing and Tracking of Concepts in LLMs
Abstract page for arXiv paper 2605.28823: What are They Thinking? Delineation, Probing and Tracking of Concepts in LLMs
[2605.28866] Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
Abstract page for arXiv paper 2605.28866: Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Langua...
[2605.28876] LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
Abstract page for arXiv paper 2605.28876: LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
[2605.28889] Context Distillation as Latent Memory Management
Abstract page for arXiv paper 2605.28889: Context Distillation as Latent Memory Management
[2605.30014] From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
Abstract page for arXiv paper 2605.30014: From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
[2605.30029] RAISE: RAG Design as an Architecture Search Problem
Abstract page for arXiv paper 2605.30029: RAISE: RAG Design as an Architecture Search Problem
[2605.30036] Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
Abstract page for arXiv paper 2605.30036: Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
[2605.30039] Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
Abstract page for arXiv paper 2605.30039: Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
[2605.30042] Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection
Abstract page for arXiv paper 2605.30042: Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection
[2605.28277] Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
Abstract page for arXiv paper 2605.28277: Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
[2605.28591] Models That Know How Evaluations Are Designed Score Safer
Abstract page for arXiv paper 2605.28591: Models That Know How Evaluations Are Designed Score Safer
[2605.28598] Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
Abstract page for arXiv paper 2605.28598: Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
[2605.28600] Transformers Provably Learn to Internalize Chain-of-Thought
Abstract page for arXiv paper 2605.28600: Transformers Provably Learn to Internalize Chain-of-Thought