DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
hub Canonical reference
Large Language Models as Optimizers
Canonical reference. 80% of citing Pith papers cite this work as background.
31
Pith papers citing it
Background
80% of classified citations
abstract
Optimization is ubiquitous. While derivative-based algorithms have been powerful tools for various problems, the absence of gradient imposes challenges on many real-world applications. In this work, we propose Optimization by PROmpting (OPRO), a simple and effective approach to leverage large language models (LLMs) as optimizers, where the optimization task is described in natural language. In each optimization step, the LLM generates new solutions from the prompt that contains previously generated solutions with their values, then the new solutions are evaluated and added to the prompt for the next optimization step. We first showcase OPRO on linear regression and traveling salesman problems, then move on to our main application in prompt optimization, where the goal is to find instructions that maximize the task accuracy. With a variety of LLMs, we demonstrate that the best prompts optimized by OPRO outperform human-designed prompts by up to 8% on GSM8K, and by up to 50% on Big-Bench Hard tasks. Code at https://github.com/google-deepmind/opro.
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
PRISM automates continuous prompt creation, simulation-based testing, diagnosis, and repair for enterprise LLM agents, cutting authoring time to under 30 minutes while reaching 99% reliability and catching drift within 24 hours.
Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
AgentFlow uses a typed graph DSL covering roles, prompts, tools, topology and protocol plus a runtime-signal feedback loop to optimize multi-agent harnesses, reaching 84.3% on TerminalBench-2 and discovering ten new zero-days in Chrome including two critical sandbox escapes.
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
NCCE reframes context engineering as instance-level recommendation via bootstrapped anchor contexts and a co-evolving neural collaborative filtering router that assigns specialized contexts per input.
AloLab, an iterative meta-agent prompt optimizer, raises structured output accuracy for 7-9B models from 0% to 84-87% on GSM8K while preserving near-native inference speed.
ContraPrompt extracts optimization rules from dyadic differences in reasoning traces on identical inputs and organizes them into input-aware decision trees, outperforming GEPA on four benchmarks with gains up to 8.29 pp.
Frontier-Eng is a new benchmark for generative optimization in engineering where agents iteratively improve designs under fixed interaction budgets using executable verifiers, with top models like GPT 5.4 showing limited success.
Pioneer Agent automates the full lifecycle of adapting and continually improving small language models via diagnosis-driven data synthesis and regression-constrained retraining, delivering gains of 1.6-83.8 points on benchmarks and large lifts in production-style tasks.
Reflective Context Learning unifies context optimization for agents by recasting prior methods as instances of a shared learning problem and extending them with classical primitives such as batching, failure replay, and grouped rollouts, yielding improvements on AppWorld, BrowseComp+, and RewardBene
Multi-agent deep research systems self-optimize prompts through self-play to match or outperform expert-crafted versions.
AutoCO couples LLM reasoning with operations-research relaxation principles and bidirectional coevolution of MCTS and EAs to solve complex constraint optimization problems more effectively than prior LLM-based approaches.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
A PPO agent with hybrid actions and test-driven rewards optimizes prompts for code LLMs, raising strict Pass@1 scores on MBPP+, HumanEval+, and APPS over prior methods.
FORGE is a staged population protocol that evolves prompt-injected memory (Rules, Examples, or Mixed) for ReAct agents via reflection and broadcast, yielding 1.7-7.7× gains over zero-shot and 29-72% over Reflexion on CybORG CAGE-2.
Iterative distillation of experience trains prompting policies that boost black-box LLM performance on reasoning and tool-use tasks from 55-74% to 90-91%.
EvE co-evolves code solvers and guidance states via synchronous races and Elo updates, discovering a rescale-then-interpolate mechanism that enables example-count generalization in ICON.
A training-free control architecture with uncertainty-based routing, confidence-selective acceptance, and evidence-based memory governance improves arithmetic reasoning by +7 points on SVAMP and ASDiv benchmarks.
Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.
MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a baby-naming benchmark.
ORFS-agent uses LLM agents to tune parameters in chip design flows, improving geometric-mean wirelength, clock period, and co-optimization objectives by up to 2.7% over OR-AutoTuner with 40% fewer iterations on ASAP7 and SKY130HD benchmarks.
citing papers explorer
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.