32 articles tagged with #prompt-optimization. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
JailbreakOPT is a new framework that optimizes adversarial prompts to exploit safety vulnerabilities in large language models through iterative refinement and tool composition. The approach combines atomic jailbreak techniques with contextual bandits to achieve higher attack success rates while reducing the number of queries needed, demonstrating meaningful progress in LLM security testing.
Researchers propose Self-Evolving Prompt Optimization (SePO), a novel system that automatically optimizes AI agent prompts by treating the prompt agent's own instructions as an optimization target. The method demonstrates consistent performance gains across five diverse benchmarks, outperforming existing approaches and showing generalization to unseen tasks.
Researchers introduce Set-Distance Rewards (SDR), a novel reinforcement learning approach for chest X-ray report generation that treats medical reports as unordered sets rather than causal chains. The method achieves 4-8% improvements over supervised fine-tuning across multiple vision-language models and enables efficient test-time scaling by pruning low-quality candidates mid-generation.
Researchers introduce Adaptive Auto-Harness, a framework that improves LLM agents' ability to handle continuous, shifting task streams by dynamically adapting prompts, skills, and tools rather than relying on static optimizations. The system decomposes performance gaps into evolution and adaptation losses, using a multi-agent evolver and intelligent routing to maintain sustained improvement across heterogeneous, open-ended task environments.
Researchers propose A2X, an LLM-native service discovery system that organizes thousands of callable services into hierarchical taxonomies to solve the context-window limitation problem facing AI agents. The approach achieves 20+ point improvements in retrieval accuracy while reducing token consumption to one-ninth compared to baseline methods, enabling scalable orchestration of distributed services.
Researchers introduce MEMENTO, a framework that treats web exploration as a learning signal for AI agents operating in data-scarce domains. By combining iterative web search with dual-channel memory systems, MEMENTO achieves 25-36% performance improvements over baseline models in professional applications like sales automation and legal research without requiring additional model training.
Researchers introduce Prompt Codebooks (PCO), a new framework for automatic prompt optimization that breaks down instructions into reusable, atomic components rather than treating prompts as fixed strings. The method achieves up to 30% performance gains over baseline approaches while reducing prompt lengths by 14x, enabling more efficient and adaptive language model instruction refinement.
A new research paper demonstrates that current LLM evaluation frameworks using static prompts across all models produce misleading rankings compared to industry practice. The study reveals that prompt optimization (PO) significantly affects model performance rankings, suggesting practitioners must optimize prompts per model for accurate comparative evaluations.
Researchers introduce ObjectGraph (.og), a new file format designed specifically for how AI agents consume documents through retrieval rather than linear reading. The format reduces token consumption by up to 95.3% while maintaining task accuracy, addressing a fundamental architectural mismatch between traditional documents and LLM agent workflows.
AlphaLab is an autonomous research system using frontier LLMs to automate experimental cycles across computational domains. Without human intervention, it explores datasets, validates frameworks, and runs large-scale experiments while accumulating domain knowledge—achieving 4.4x speedups in CUDA optimization, 22% lower validation loss in LLM pretraining, and 23-25% improvements in traffic forecasting.
Researchers introduce MASPOB, a bandit-based framework that optimizes prompts for Multi-Agent Systems using Graph Neural Networks to handle topology-induced coupling. The system reduces search complexity from exponential to linear while achieving state-of-the-art performance across benchmarks.
Researchers developed a hierarchical multi-agent LLM framework that significantly improves multi-robot task planning by combining natural language processing with classical PDDL planners. The system uses prompt optimization and meta-learning to achieve success rates of up to 95% on compound tasks, outperforming previous state-of-the-art methods by substantial margins.
Researchers introduce RIZZ, a black-box adaptation framework for large language models deployed as long-lived agents that must continually adapt across diverse tasks and domains without access to model weights. The system uses verifier-gated memory, dynamic routing, and prompt compilation to prevent task interference while learning from sparse feedback in nonstationary environments.
APEX introduces a data-efficient framework for automatic prompt optimization in large language models by dynamically categorizing training data into Easy, Hard, and Mixed tiers. The system prioritizes Mixed-tier data to identify high-leverage subsets that improve prompt quality, achieving 11.2% performance gains on Gemini 2.5 Flash with 40% fewer evaluations than static approaches.
Researchers introduce Regimes, an auditable autonomous improvement loop built on the ActiveGraph event-sourced runtime that enables transparent, reproducible AI agent optimization. The system diagnoses failures, proposes repairs, and validates them through multiple gates before promotion, demonstrating 5-10% held-out accuracy improvements on long-context reading comprehension tasks.
Researchers introduce 'handoff debt,' a framework measuring the efficiency cost when coding agents resume interrupted tasks from incomplete states. Testing across 75 tasks and 724 takeover runs, they found that providing context-bearing handoff information (traces, notes, structured documentation) reduces agent event counts by 20-59% and token consumption by 42-63% compared to repository-only takeover, suggesting current agent benchmarks underestimate real-world deployment costs.
Researchers introduce Demo2Reward, a test-time optimization technique that improves Vision-Language Model (VLM) reward models by refining prompts based on a small number of expert demonstrations. The method reduces false positives in reward prediction without requiring additional model training, enabling more effective reinforcement learning in robotics applications including real-world scenarios.
Researchers present HOPM, a hierarchical prompt mutation framework that adaptively optimizes language model outputs for high-stakes document generation in marketplace dispute resolution. Testing on 600 real cases, the system achieved an 11 percentage point improvement in win rate and 19.1 percentage point improvement in amount-weighted outcomes compared to static prompting, combining human feedback with automated evaluation.
Researchers introduce a unified evaluation-instructed framework for optimizing AI prompts that adapts to individual queries rather than using static templates. The approach combines a systematic prompt evaluation framework with an execution-free evaluator that predicts quality scores and guides a metric-aware optimizer to rewrite prompts in an interpretable, query-dependent manner, demonstrating consistent improvements across multiple datasets and models.
Researchers introduce eXTC, a new framework combining structured prompt optimization with reinforcement learning to create interpretable text classifiers that balance performance with explainability. The system generates human-readable domain rules while maintaining inference speed through knowledge distillation, addressing a longstanding trade-off in AI transparency.
TCP-MCP introduces a co-evolution framework that simultaneously optimizes AI agent prompts and communication network topologies, achieving state-of-the-art accuracy on multiple benchmarks while reducing token consumption by up to 5.69x compared to existing multi-agent systems. The approach treats prompt design and communication structure as interdependent variables rather than independent parameters, offering a practical methodology for cost-efficient multi-agent AI system design.
Researchers introduce MemTrace, a framework for debugging Large Language Model memory systems by tracing information flow through memory evolution graphs. The system identifies root causes of memory failures and uses attribution signals to automatically optimize prompts, achieving up to 7.62% performance improvements across multiple memory architectures.
Researchers introduce PICACO, a novel in-context alignment method that optimizes meta-instructions to help large language models better understand and balance multiple, often conflicting human values without fine-tuning. The approach uses total correlation optimization to improve alignment across up to 8 distinct values while reducing noise, addressing a key limitation where LLMs struggle to reconcile competing preferences in single prompts.
Researchers introduce EGL-SCA, a framework for graph reasoning agents that jointly optimizes both natural language instructions and computational tools through structural credit assignment. The system achieves 92.0% success rate on graph reasoning benchmarks by precisely routing failures to either prompt optimization or tool synthesis, outperforming isolated improvement approaches.
Researchers demonstrate that self-consistency—a technique where LLMs sample multiple reasoning paths to improve accuracy—delivers diminishing returns on modern models. Testing with Gemini 2.5 shows minimal accuracy gains (0.4-1.6%) while token costs scale linearly, suggesting the technique has become inefficient as model reliability improves.
