managing-context-explicitly-paging-information-out-bounded-window CLM-0084mechanismsingle paperReviewed by AI and Russ Miller
Managing context explicitly, paging information in and out of a bounded window, sustains performance on tasks that exceed the window.
Evidence for: Lehman's law of increasing complexity (holds)
Capability: Keeping its own context clean
Sources
- Managing context explicitly, paging information in and out of a bounded window, sustains performance on tasks that exceed the window.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- A tiered memory system managed by the model itself sustains recall over conversations far longer than the context window.Remembering across sessions
- Holding the task fixed and only lengthening the input degrades reasoning long before the context limit is reached.Losing information in long inputs
- On web-browsing (WebArena, Mind2Web) and software-engineering (SWE-Bench-Verified) benchmarks, an agent that distills reusable strategies from both its successful and its failed attempts, judged by an LLM without ground truth, and retrieves the relevant ones on later tasks, outperforms memories that store raw trajectories or only successful routines — up to 20% relative improvement in success and up to 16% fewer interaction steps — with the weights unchanged; including the failures is part of the gain, not noise.Improving its own scaffolding from failures · reviewed by AI
- For memory-augmented VLA manipulation policies that must actively move the viewpoint to find task-relevant evidence, writing one memory frame at each fixed action-chunk boundary generalizes better than event-triggered writing (on predicted subtask change or on gripper/head/torso motion), and extra memory capacity helps only under the regular schedule — event-triggered policies degrade further out of distribution because mistimed triggers omit informative views and control jitter fills memory with redundant frames.Turning plans into physical action · reviewed by AI