Dynamic context discovery · Cursor

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve usability but often suffer from brevity bias, which drops domain insights for concise summaries, and from context collapse, where iterative rewriting erodes details over time. We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation. ACE prevents collapse with structured, incremental updates that preserve detailed knowledge and scale with long-context models. Across agent and domain-specific benchmarks, ACE optimizes contexts both offline (e.g., system prompts) and online (e.g., agent memory), consistently outperforming strong baselines: +10.6% on agents and +8.6% on finance, while significantly reducing adaptation latency and rollout cost. Notably, ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback. On the AppWorld leaderboard, ACE matches the top-ranked production-level agent on the overall average and surpasses it on the harder test-challenge split, despite using a smaller open-source model. These results show that comprehensive, evolving contexts enable scalable, efficient, and self-improving LLM systems with low overhead.

Context Engineering

Context engineering strategies for AI agents: write, select, compress, and isolate context to optimize performance and manage long-running tasks.

Introducing Cursor 2.0 and Composer · Cursor

A new interface and our first coding model, both purpose-built for working with agents.

Context Constitution

Today we are releasing the Context Constitution: a set of principles governing how AI agents manage context to learn from experience.

Joshua Gu on Twitter / X

Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.🚨 While this is a good idea, we show a surprising result: systems… pic.twitter.com/XHFVaDcr4l— Joshua Gu (@astrogu_) May 20, 2026

Model Leaderboard | Letta

Context-Bench measures an agent's ability to perform context engineering with:

AI Coding: Managing Context

Managing your coding agent's context is super important - a bloated context window will erode the quality of your agent's work over time. Learn some new techniques for trimming irrelevant details from your conversation history while retaining what matters.

Cursor: AI coding agent

Built to make you extraordinarily productive, Cursor is the best AI coding agent.

Meet the new Cursor · Cursor

Cursor 3 is a unified workspace for building software with agents.

Memory in Agents: What, Why and How

LLM memory gives language models persistent context across sessions. Learn how it works, how it differs from RAG and context windows, and how to add LLM memory to your agents with Mem0.

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.

Context Engineering for AI Agents: Lessons from Building Manus

This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.

Dii familiares

Musings on agents and AI and a little signposting

Context Engineering | Meetup

"Context engineering is the delicate art and science of filling the context window with just the right information for the next step" - Andrej KarpathyLearn about tools, frameworks, and code that is in service of context engineering from practitioners in this space.Dive into the set of strategies fo

Code execution with MCP: building more efficient AI agents

Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context overhead by up to 98.7%.