Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
On the map: LLM reasoning → Prompting and chain-of-thought reasoning
Abstract (arXiv)
While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts. Recent evaluations on the CL-Bench reveal a critical capability gap: frontier models solve only 17.2% of context-dependent tasks on average.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 51 references that are in the map. First posted on arXiv 25 May 2026.
Builds on
27 of 51 references.
Closest ancestors · 8
Same direction, newest first
- 2026Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection3 Apr
- 2026Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation16 Feb
- 2025CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning15 Oct
- 2025Merge-of-Thought Distillation10 Sep
- 2025Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning13 Aug
- 2025CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks31 Jul
- 2022Teaching Small Language Models to Reason16 Dec
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan
Other references · 19
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
- 2023Let's Verify Step by Stepcited by 3,598
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
- 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
- 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
- 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
- 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
- 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
- 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
- 2024The Prompt Report: A Systematic Survey of Prompt Engineering Techniquescited by 115
- 2024Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systemscited by 87
7 more
- 2026CL-bench: A Benchmark for Context Learningcited by 46
- 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 26
- 2026Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Taskscited by 23
- 2025Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflictcited by 15
- 2026CL-bench Life: Can Language Models Learn from Real-Life Context?cited by 8
- 2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agentscited by 7
- 2026DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignmentcited by 7
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
- 2025Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
- 2025Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling
- 2025When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
- 2025To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
- 2023Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
- 2026Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought
- 2026Agentic Context Learning with Self-Discovered Specification