DeepMind's AlphaEvolve broke a 56-year-old record by multiplying 4x4 matrices in 48 scalar multiplications, while recovering 0.7% of Google's worldwide compute and cutting Gemini's training time by 1%…
Researchers introduced Contrastive Reflection, an iterative prompt-optimization framework for agentic information retrieval workflows, which uses error-anchored behavioral slices and contrastive examp…
A new open-source tool called World Model Harness (wmh) uses frontier LLMs to simulate agent environments from OpenTelemetry traces, replacing traditional sandboxes. The tool ingests recorded state-ac…
Researchers introduced RSEA, a Recursive Self-Evolving Agent that improves LLM agents by rewriting natural-language artifacts without weight updates, using a held-out selection gate to prevent regress…
A new benchmark, dspy-security-bench, reveals that DSPy prompt optimization degrades adversarial robustness against harder prompt-injection attacks. Testing with AgentDojo's attack suite, optimizers l…
Researchers at UC Berkeley introduced LEVI, an AI-driven framework that optimizes systems algorithms at 3-7 times lower cost than existing methods. By using smaller, cheaper models for most mutations …
AxLLM launches Ax, a multi-language LLM framework that uses typed signatures to replace prompt glue with automated prompt generation, parsing, validation, and retry loops. Built on research from DSPy,…
Researchers introduced GEPA, a prompt optimizer that uses an LLM to read execution traces and rewrite prompts, outperforming reinforcement learning by leveraging natural language reasoning about failu…
Cisco Foundation AI open-sourced FAPO, a Claude Code-driven system that autonomously optimizes multi-step LLM pipelines by attributing failures at the step level and proposing variants. In evaluations…
AgentArk has released a Personal AI OS on GitHub, described as a security-first, self-learning operating system for AI agents. The open-source repository, agentark-ai/AgentArk, offers developers a cod…
Decagon deployed self-evolving AI agents that automatically improve their own prompts without human intervention, using a feedback loop that tests and promotes winning versions. The team found that th…
A developer built an evaluation framework for AI agents that combines deterministic metrics with an optional LLM judge. The framework runs agents as isolated subprocesses, scores them on five determin…
A developer has created Genetic-Pareto Prompt Evolution (GEPA), a system that automates prompt optimization for AI agents by treating prompts as genomes that evolve through mutation and crossover. The…
Researchers introduced SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a code-augmented agentic optimizer that autonomously rewrites prompts using a Python sandbox for structural error analys…