A brand new framework from Stanford College and SambaNova addresses a crucial problem in constructing strong AI brokers: context engineering. Referred to as Agentic Context Engineering (ACE), the framework mechanically populates and modifies the context window of enormous language mannequin (LLM) functions by treating it as an “evolving playbook” that creates and refines methods because the agent features expertise in its setting.
ACE is designed to beat key limitations of different context-engineering frameworks, stopping the mannequin’s context from degrading because it accumulates extra data. Experiments present that ACE works for each optimizing system prompts and managing an agent's reminiscence, outperforming different strategies whereas additionally being considerably extra environment friendly.
The problem of context engineering
Superior AI functions that use LLMs largely depend on "context adaptation," or context engineering, to information their habits. As an alternative of the expensive means of retraining or fine-tuning the mannequin, builders use the LLM’s in-context studying skills to information its habits by modifying the enter prompts with particular directions, reasoning steps, or domain-specific data. This extra data is normally obtained because the agent interacts with its setting and gathers new information and expertise. The important thing objective of context engineering is to arrange this new data in a approach that improves the mannequin’s efficiency and avoids complicated it. This method is turning into a central paradigm for constructing succesful, scalable, and self-improving AI programs.
Context engineering has a number of benefits for enterprise functions. Contexts are interpretable for each customers and builders, could be up to date with new data at runtime, and could be shared throughout completely different fashions. Context engineering additionally advantages from ongoing {hardware} and software program advances, such because the rising context home windows of LLMs and environment friendly inference strategies like immediate and context caching.
There are numerous automated context-engineering strategies, however most of them face two key limitations. The primary is a “brevity bias,” the place immediate optimization strategies are likely to favor concise, generic directions over complete, detailed ones. This will undermine efficiency in advanced domains.
The second, extra extreme subject is "context collapse." When an LLM is tasked with repeatedly rewriting its complete collected context, it may well endure from a sort of digital amnesia.
“What we name ‘context collapse’ occurs when an AI tries to rewrite or compress every thing it has discovered right into a single new model of its immediate or reminiscence,” the researchers stated in written feedback to VentureBeat. “Over time, that rewriting course of erases necessary particulars—like overwriting a doc so many occasions that key notes disappear. In customer-facing programs, this might imply a assist agent abruptly dropping consciousness of previous interactions… inflicting erratic or inconsistent habits.”
The researchers argue that “contexts ought to perform not as concise summaries, however as complete, evolving playbooks—detailed, inclusive, and wealthy with area insights.” This method leans into the power of recent LLMs, which might successfully distill relevance from lengthy and detailed contexts.
How Agentic Context Engineering (ACE) works
ACE is a framework for complete context adaptation designed for each offline duties, like system immediate optimization, and on-line situations, akin to real-time reminiscence updates for brokers. Fairly than compressing data, ACE treats the context like a dynamic playbook that gathers and organizes methods over time.
The framework divides the labor throughout three specialised roles: a Generator, a Reflector, and a Curator. This modular design is impressed by “how people study—experimenting, reflecting, and consolidating—whereas avoiding the bottleneck of overloading a single mannequin with all obligations,” in line with the paper.
The workflow begins with the Generator, which produces reasoning paths for enter prompts, highlighting each efficient methods and customary errors. The Reflector then analyzes these paths to extract key classes. Lastly, the Curator synthesizes these classes into compact updates and merges them into the prevailing playbook.
To stop context collapse and brevity bias, ACE incorporates two key design rules. First, it makes use of incremental updates. The context is represented as a group of structured, itemized bullets as an alternative of a single block of textual content. This enables ACE to make granular modifications and retrieve probably the most related data with out rewriting the complete context.
Second, ACE makes use of a “grow-and-refine” mechanism. As new experiences are gathered, new bullets are appended to the playbook and present ones are up to date. A de-duplication step usually removes redundant entries, making certain the context stays complete but related and compact over time.
ACE in motion
The researchers evaluated ACE on two kinds of duties that profit from evolving context: agent benchmarks requiring multi-turn reasoning and gear use, and domain-specific monetary evaluation benchmarks demanding specialised data. For top-stakes industries like finance, the advantages prolong past pure efficiency. Because the researchers stated, the framework is “much more clear: a compliance officer can actually learn what the AI discovered, because it’s saved in human-readable textual content fairly than hidden in billions of parameters.”
The outcomes confirmed that ACE constantly outperformed sturdy baselines akin to GEPA and basic in-context studying, attaining common efficiency features of 10.6% on agent duties and eight.6% on domain-specific benchmarks in each offline and on-line settings.
Critically, ACE can construct efficient contexts by analyzing the suggestions from its actions and setting as an alternative of requiring manually labeled information. The researchers word that this capacity is a "key ingredient for self-improving LLMs and brokers." On the general public AppWorld benchmark, designed to judge agentic programs, an agent utilizing ACE with a smaller open-source mannequin (DeepSeek-V3.1) matched the efficiency of the top-ranked, GPT-4.1-powered agent on common and surpassed it on the harder take a look at set.
The takeaway for companies is important. “This implies corporations don’t must rely on large proprietary fashions to remain aggressive,” the analysis crew stated. “They’ll deploy native fashions, defend delicate information, and nonetheless get top-tier outcomes by constantly refining context as an alternative of retraining weights.”
Past accuracy, ACE proved to be extremely environment friendly. It adapts to new duties with a median 86.9% decrease latency than present strategies and requires fewer steps and tokens. The researchers level out that this effectivity demonstrates that “scalable self-improvement could be achieved with each increased accuracy and decrease overhead.”
For enterprises involved about inference prices, the researchers level out that the longer contexts produced by ACE don’t translate to proportionally increased prices. Fashionable serving infrastructures are more and more optimized for long-context workloads with strategies like KV cache reuse, compression, and offloading, which amortize the price of dealing with intensive context.
In the end, ACE factors towards a future the place AI programs are dynamic and constantly enhancing. "Right now, solely AI engineers can replace fashions, however context engineering opens the door for area consultants—attorneys, analysts, docs—to instantly form what the AI is aware of by modifying its contextual playbook," the researchers stated. This additionally makes governance extra sensible. "Selective unlearning turns into way more tractable: if a chunk of data is outdated or legally delicate, it may well merely be eliminated or changed within the context, with out retraining the mannequin.”
