# ICL Optimized Fragility

arXiv: https://arxiv.org/abs/2510.00300 · HTML: https://mlsanity.com/paper/2510.00300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 6 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models](https://mlsanity.com/paper/2409.15454/) (2024)
- [The ICL Consistency Test](https://mlsanity.com/paper/2312.04945/) (2023)
- [Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects](https://mlsanity.com/paper/2509.04794/) (2025)

## Abstract (arXiv)

ICL guides are known to improve task-specific performance, but their impact on cross-domain cognitive abilities remains unexplored. This study examines how ICL guides affect reasoning across different knowledge domains using six variants of the GPT-OSS:20b model: one baseline model and five ICL configurations (simple, chain-of-thought, random, appended text, and symbolic language). The models were subjected to 840 tests spanning general knowledge questions, logic riddles, and a mathematical olympiad problem. Statistical analysis (ANOVA) revealed significant behavioral modifications (p less than 0.001) across ICL variants, demonstrating a phenomenon termed "optimized fragility." ICL models achieved 91%-99% accuracy on general knowledge tasks while showing degraded performance on complex reasoning problems, with accuracy dropping to 10-43% on riddles compared to 43% for the baseline model. Notably, no significant differences emerged on the olympiad problem (p=0.2173), suggesting that complex mathematical reasoning remains unaffected by ICL optimization. These findings indicate that ICL guides create systematic trade-offs between efficiency and reasoning flexibility, with important implications for LLM deployment and AI safety.