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.
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.
arXiv:2607. 20064v1 Announce Type: new Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents.
Long sessions rot quietly, well before any token limit is reached. Here’s why, and how to govern your context in Claude Code.
arXiv:2607. 17621v1 Announce Type: new Abstract: Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections.
arXiv:2607. 08180v1 Announce Type: cross Abstract: The rise of LLM-based agents with reasoning, summarization, and memory capabilities has created a new threat surface for online content that conventional defenses fail to address.
arXiv:2606. 05646v1 Announce Type: cross Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues.
arXiv:2607. 01916v1 Announce Type: new Abstract: Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where useful evidence is mixed with irrelevant code and logs.