LLM Input Optimization

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

22 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize
Sep 3, 2026Lihao Liu, Peng Tang, Kunwar Yashraj Singh +1Evolutionary Optimization Large Language Model-Guided Optimization
AWS Agentic AI
SEPO: Evidence-Grounded Prompt Optimization via Structural Editing
Aug 28, 2026Xiaoyu Ma, Haoyue Liu, Yiwen Li +4Automatic Prompt Optimization Prompt Optimization
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · Xi’an Jiaotong University · Shenzhen Future Network of Intelligence Institute (FNiI-Shenzhen) +1
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
Aug 11, 2026Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi +1Large Language Model-Guided Optimization LLM Agents
Autonomize AI · Carnegie Mellon University
Moral Hazard in Multi-Agent Language Models
Jul 27, 2026Dane MalenfantLLM Input Optimization LLM Prompting
School of Computer Science · McGill University · Mila - The Québec AI Institute
Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems
Jun 12, 2026Tan Zhu, Tong Yao, Kananart Kuwaranancharoen +4Multi-Agent LLM Systems LLM Input Optimization
Retail Intelligence, Walmart Global Tech, Sunnyvale, CA, USA
Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers
May 9, 2026Aditya RanganathDeep Learning Optimization LLM Input Optimization
Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore, CA, USA
Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio
May 7, 2026Ziqing Wen, Zhouyang Liu, Jiahuan Wang +4Deep Learning Optimization LLM Input Optimization
College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China
Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
May 6, 2026Mikhail L. Arbuzov, Sisong Bei, Ziwei Dong +2LLM Compression Prompt Compression
Independent Researcher · Palo Alto Networks
When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
May 4, 2026Cosimo Galeone, Minsu Park, Giuseppe Ettorre +1LLM Evaluation LLM Input Optimization
Alomana, Grottaglie, Italy
Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading
Apr 30, 2026Nicholas Sadjoli, Tim Siefken, Atin Ghosh +2LLM Evaluation Language Model Generation Evaluation
SAP · Stanford University
Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy
Apr 19, 2026Amr AhmedLLM Prompting Prompt Optimization
Public Health Department, Riyadh First Health Cluster · Ministry of Health, Saudi Arabia
ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization
Apr 19, 2026Harshavardhanan DeekeswarLLM Inference Efficiency LLM Input Optimization
Independent Researcher · Chennai, India
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
Apr 13, 2026Yuqing Yang, Tengxiao Liu, Wang Bill Zhu +3LLM Input Optimization LLM Memory
University of Southern California · University of California, Santa Barbara
SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
Apr 9, 2026Wooin Lee, Hyun-Tae KimLLM Input Optimization Memory-Efficient Optimization
London, United Kingdom · Seoul, Republic of Korea
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Apr 8, 2026Haoyue Liu, Zhichao Wang, Yongxin Guo +2LLM Input Optimization LLM Prompting
The Chinese University of Hong Kong, Shenzhen · Taobao and Tmall Group
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Apr 5, 2026Hanchen Li, Runyuan He, Qizheng Zhang +11LLM Input Optimization LLM Prompting
UC Berkeley · Stanford University · Independent +1
Do We Need Frontier Models to Verify Mathematical Proofs?
Apr 2, 2026Aaditya Naik, Guruprerana Shabadi, Rajeev Alur +1LLM Input Optimization Reasoning Verification
University of Pennsylvania, U.S.A.
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models
Mar 27, 2026Rahul SoniLLM Input Optimization LLM Prompting
Independent Researcher
Enhancing LLM Training via Spectral Clipping
Mar 15, 2026Xiaowen Jiang, Andrei Semenov, Sebastian U. StichLLM Input Optimization Spectral Regularization
CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Universität des Saarlandes, Saarbrücken, Germany · EPFL
NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
Mar 4, 2026Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe +7LLM Input Optimization LLM Compression
Pluralis Research
How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
Feb 23, 2026Wei Chen, Guoyang Ju, Yuanyuan QiLLM Input Optimization LLM Prompting
China Jiliang University, Hangzhou, China
BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models
Nov 7, 2025Chandra Vamsi Krishna Alla, Harish Naidu Gaddam, Manohar Kommi +1Memory-Efficient Optimization LLM Compression
University of Texas at Arlington

Sep 3, 2026J/K move · Enter open · S save

ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize

Lihao Liu, Peng Tang, Kunwar Yashraj Singh, Shabnam Ghadar

AWS Agentic AI

Evolutionary Optimization Large Language Model-Guided Optimization Automatic Prompt Optimization LLM Input Optimization

Open paper AskPDF arXiv

Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, producing prompts up to 3

\times

longer yet no more accurate. We trace this to three deficiencies - incomplete error observation, limited search diversity, and unreliable selection - and propose ESPO (Error-Structured Prompt Optimization), which decomposes prompt optimization into three phases: Diagnose clusters all training errors into structural patterns in one round; Propose generates candidates via four complementary strategies with independent biases; Select applies bootstrap stability selection. On seven public NLP benchmarks - Tweet, MMLU, GSM8K, HotpotQA, ScoNe, HoVer, and PUPA - ESPO improves average accuracy by

+

3.76 pp over the state-of-the-art (74.67% vs 70.91% for GEPA), matching or exceeding GEPA on every dataset while producing prompts 47% shorter (1,004 vs 1,878 chars) and faster at inference. Cross-model experiments across four additional student models (Gemma 3 12B, Mistral 14B, Qwen3 32B, Claude Haiku 4.5) show ESPO yields the best average accuracy on every model tested, with the largest gap on Qwen3 GSM8K (15.00%

\to

91.40%). A generalization bound (Appendix) grounds each phase in a corresponding term of the test-time gap, and the ablation confirms a key prediction: adding diversity without bootstrap selection actually hurts performance (

-

1.20%).