Noah Shinn launched shareable Files for Instinct on September 18th, letting the AI personal assistant turn its work into private or public interactive pages users can send to others. Instinct creates …
An agent harness is the code and structure around a language model that converts raw text prediction into goal-directed behavior, and it has driven larger performance gains than model upgrades, accord…
Noah Goodman's former student and MIT collaborator, who co-created Reflexion, hypothesizes that Instinct's appeal stems from its memory architecture rather than its agentic engine, marking a third wav…
Agentic Context Engineering (ACE) improves LLM systems by evolving their context instead of their weights, using three agents—Generator, Reflector, and Curator—to maintain a playbook through small, de…
A new tutorial from Anthropic demonstrates that AI agents can reliably self-correct only when grounded in external verification, citing a 2024 paper showing large language models cannot self-correct r…
A 2026 analysis identifies five foundational papers—ReAct, Toolformer, Reflexion, Voyager, and an unnamed framework paper—that underpin every modern AI agent architecture, tracing the tool-calling loo…
Researchers have identified a new attack surface against multi-hop retrieval-augmented generation (RAG) agents called Salience Induction, which uses truth-preserving edits to redirect reasoning withou…
A new closed-loop framework for AI coding agents, deployed across a microservices platform with over 35 services, embeds human feedback as behavioral rules to enable persistent improvement without tra…
Researchers introduced Reflexion, an AI-powered prototype for structured emotional self-reflection that integrates emotion detection, layered prompting, and metaphorical storytelling. The system guide…
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…
Large language models are stateless by default, but agents require memory to retain context across steps. A new technical guide identifies seven types of agent memory—working, semantic, episodic, proc…