Most coding agents treat prompt construction like retrieval: gather more files, add more context, hope the model figures it out. But that approach breaks down fast.
Summary generated by The Flow from the publisher's feed. The full article lives at Towards Data Science.
arXiv:2607. 23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment.
Most AI memory systems keep the newest information—not the most important. Here's how I used the Ebbinghaus forgetting curve to build a better memory engine for LLMs.
arXiv:2510. 00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observations.
LLMs don’t fail because they forget—they fail because they remember too much. As conversations grow, prompts accumulate redundant and low-value tokens, driving up cost and latency while silently degrading output quality.
Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn a compression policy that discards evidence or manage context in a layer the agent never sees.
arXiv:2608. 06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood.