AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

Guancheng Wan, Lucheng Fu, Haoxin Liu, Yiqiao Jin, Hui Yi Leong, Eric Hanchen Jiang, Hejia Geng, Jinhe Bi, Yunpu Ma, Xiangru Tang, B. Aditya Prakash, Yizhou Sun and 1 more

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add anisotropic adaptive search (ATARE over TARE)TARE, Llama 3.1 8B Instruct · Tracking Shuffled Objects (GPT-4o)accuracy (%): 90.0 -> 93.5Improved
add anisotropic adaptive search (ATARE over TARE)TARE, Llama 3 8B Instruct · Object Counting (Claude 3.5 Sonnet)accuracy (%): 89.5 -> 93.6Improved
add anisotropic adaptive search (ATARE over TARE)TARE, Llama 3.1 8B Instruct · GSM8K (GPT-4o)accuracy (%): 86.2 -> 86.4No clear effect
use TARE instead of TextGradTextGrad, Llama 3.1 8B Instruct · Object Counting (GPT-4o)accuracy (%): 88.6 -> 91.0Improved
use ATARE instead of TextGradTextGrad, Llama 3.1 8B Instruct · Tracking Shuffled Objects (GPT-4o)accuracy (%): 86.3 -> 93.5Improved
use ATARE instead of TextGradTextGrad, GPT-4o · GPQAaccuracy (%): 52.5 -> 53.0Improved
use ATARE instead of TextGradTextGrad, Llama 3.1 8B Instruct · GPQAaccuracy (%): 30.8 -> 33.8Improved
use ATARE instead of TextGradTextGrad, Qwen 2.5 7B Instruct · MMLU College Physicsaccuracy (%): 78.4 -> 79.4Improved
use ATARE instead of TextGradTextGrad, Llama 3 8B Instruct · GSM8K (GPT-4o)accuracy (%): 81.8 -> 81.8No clear effect
remove inner adversarial search, LATO or robust validation (ablation)TARE/ATARE, Llama 3.1 8B Instruct · ablation (figure)accuracy (%)Improved
replace Generator or Optimizer oracle with Llama 3.1 8B (ablation)TARE/ATARE · BBH tasksaccuracy (%): within 5% marginNo clear effect
reduce search budgets K_t and K~ from 3 to 1 or 2 (ablation)TARE/ATARE · BBH tasksaccuracy (%)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy