Anthropic Finds Selective Forgetting Beats Exhaustive Memory for AI Agents
Anthropic studied how Claude retains knowledge across sessions and found that selectively recording strategies and rules outperforms exhaustive logging, which floods models with outdated data. Its post-session "Dreaming" process analyzes past transcripts during idle periods to correct faulty notes and build structured knowledge collections.
Related Entities
Full Report
Contents5 sections
Anthropic says the key to agent memory is knowing what to forget, not how much to store
[Jonathan Kemper](https://the-decoder.com/author/jonathan-kemper/) [View the LinkedIn Profile of Jonathan Kemper](https://www.linkedin.com/in/jonathankemper/) Nov 16, 2026 
Anthropic
Key Points
-
Anthropic tested how Claude can store information in note files across sessions and retrieve it for later tasks.
-
The tests showed that selectively recording strategies and rules works better than logging every step, which overwhelms models with outdated data.
-
Through a post-session process called "Dreaming," the system analyzes earlier session transcripts during idle periods to independently correct faulty notes and build structured knowledge collections.
Text Ask about this article… Search
Anthropic studied how Claude retains knowledge across sessions. Its tests show that selective notes outperform exhaustive archives and that having Claude review its own memories after the fact can correct errors.
Anyone who works with an AI agent on a project over several days hits a wall fast, because every new session starts from scratch. In a research post, Anthropic describes how Claude is supposed to retain knowledge across sessions while the model stays unchanged. Claude writes notes to a folder that it can read back later.
The core problem, according to Anthropic, is selection. Before it knows what comes next, the agent has to decide in the moment what might matter later, so every note is a bet on the future.
Ad
A wrong note about the Pokémon Center's location caused Claude to repeatedly fall back over a ledge. | Image: Anthropic
Agents that save everything lose track
In an Anthropic test with Pokémon Red, the older Claude Sonnet 3.7 treated everything as potentially important and, across roughly 10,000 game steps, created 413 files in 225 folders, often a separate one for each battle and item it found. Because the game state keeps changing, the archive goes stale fast. At times, the model did nothing but reorganize its notes instead of playing, and it finished with just a single badge.
The newer Claude Fable 5 limited its memory to a few files and earned four badges. Fable 5 didn't record information already visible on screen and instead wrote down plans, strategies, and rules it had tested. Anthropic's comparison, however, covers only a single playthrough per model.
Sonnet 3.7 saved nearly everything while playing Pokémon, whereas Fable 5 saved only strategies and verified rules and got much further. | Image: Anthropic
Anthropic recommends explaining the purpose of memory to Claude and letting the model decide how to use it. In one benchmark, according to Anthropic, rigid instructions such as "only record mistakes" wiped out most of the advantage for stronger models. Older models, by contrast, benefited from clear instructions, such as being told to actually read their notes before every response.
Ad
Specific memory rules help older models, while stronger models perform worse with rigid instructions. | Image: Anthropic
Dreaming aims to fix false memories
The bigger risk comes from faulty notes that the agent blindly trusts later. Dreaming, an idea that builds on research from Letta and UC Berkeley, is designed to address this. Much like the human brain processes experiences during sleep, Claude goes through transcripts of earlier sessions during a break and checks its notes against them.
During "Dreaming," Claude processes old transcripts in idle periods and builds the upper layers of its memory from them. | Image: Anthropic
In the Pokémon test, Claude had incorrectly noted which side of a mountain a landmark was on. Relying on that faulty note, Claude fell into the same trap three times, eventually wanted to give up, and missed its goal. After a Dreaming pass, Claude caught the error by checking the note against the transcript and found the right path.
Ad
Claude made it past Mt. Moon to Cerulean City only with the note Dreaming had corrected. | Image: Anthropic
According to Anthropic, Dreaming can also organize larger knowledge bases. Claude built a linked wiki from about 350,000 internal documents from Stainless, a software company Anthropic acquired. Dreaming is supposed to generate new pages while fixing gaps, duplicates, and broken links. The payoff was greatest when Claude could combine the wiki with search, so the wiki worked as a complement rather than a replacement.
Ad
The longer Claude worked on the wiki of Stainless documents, the better it answered questions, with the best results coming from combining the wiki with search. | Image: Anthropic
In a separate legal test by Anthropic, a wiki helped most with questions whose answers were spread across multiple documents. Claude scored 87 percent with the wiki, compared to 73 percent with search alone. For simple lookup tasks, the wiki performed roughly on par with search, and in one case it even grew larger than the source documents.
Memory is still a work in progress
Anthropic acknowledges that key questions remain open. Taking notes mid-task distracts the agent from its work, Dreaming costs extra compute, and its results arrive only after a delay. Wikis and notes also need regular upkeep, or errors and hallucinations pile up. Anthropic also warns against automatically loading too many memories into every session, because they eat up context and pass any bad note along to every future session.
All of these tests come from Anthropic. The overall takeaway is that a useful agent memory depends less on storing as much as possible than on keeping the right information and correcting mistakes later.
Anthropic introduced Dreaming in May as a research preview for Claude Managed Agents, the company's cloud platform for AI agents. The service reads an existing memory store and up to 100 past sessions, removes duplicate and outdated entries, and creates a reorganized store, leaving the original untouched. At launch, Dreaming supported only Claude Opus 4.7 and Sonnet 4.6.
OpenAI also calls ChatGPT's memory, which it overhauled in June, "Dreaming." That system maintains a user profile in the background and automatically corrects outdated information. According to OpenAI, this raised temporal accuracy from 52.2 to 75.1 percent.
Researchers at Google and Google DeepMind also let AI agents dream, but they use dreaming to improve an agent's search strategy. Their agent works through alternative solutions using results it has already stored, without calling the model again. Google has also built WikiSkill, a wiki for agents. As in Anthropic's system, WikiSkill keeps raw transcripts, distilled knowledge, and specific instructions in separate layers.