mlsanityData to 14 Oct 2026

Evolutionary Context Search for Automated Skill Acquisition

arXiv 2602.16113 ↗First posted 18 Feb 2026cs.NE cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge without retraining. Retrieval-Augmented Generation attempts to bridge this gap by surfacing relevant documents at inference time, yet similarity-based retrieval often fails to identify context that actually improves task performance. We introduce Evolutionary Context Search (ECS), an evolutionary method that searches context combinations using accuracy on a small development set, requiring only inference calls without weight updates. ECS moves beyond semantic similarity to discover non-obvious context pairings that significantly boost performance. Our empirical results show that ECS improves BackendBench by 27% and τ-bench airline by 7%. The evolved contexts are model-agnostic, as those evolved with Gemini-3-Flash transfer effectively to Claude Sonnet and DeepSeek. This suggests that ECS opens a path toward automated context discovery for skill acquisition -- an efficient alternative to manual prompt engineering or costly fine-tuning.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

35 of 47 references.

References · 35

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  11. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
23 more
  1. 2021GPT Understands, Toocited by 716
  2. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  3. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  4. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  5. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  6. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  7. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 542
  8. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  9. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  10. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  11. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  12. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  13. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 234
  14. 2020How Context Affects Language Models' Factual Predictionscited by 181
  15. 2022Large Language Models with Controllable Working Memorycited by 169
  16. 2024HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuningcited by 123
  17. 2024The rising costs of training frontier AI modelscited by 95
  18. 2022Revisiting Parameter-Efficient Tuning: Are We Really There Yet?cited by 76
  19. 2023Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledgecited by 67
  20. 2023On the Effectiveness of Large Language Models in Domain-Specific Code Generationcited by 44
  21. 2023Unveiling the Pitfalls of Knowledge Editing for Large Language Modelscited by 43
  22. 2024FACTS About Building Retrieval Augmented Generation-based Chatbotscited by 15
  23. 2024Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuationscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Assessing an evolutionary search engine for small language models, prompts, and evaluation metrics ↗
  2. 2026Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling
  3. 2026SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
  4. 2026ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
  5. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
  6. 2026ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
  7. 2025Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
  8. 2025Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation