arXiv:2606. 05720v1 Announce Type: cross Abstract: Large language models and AI coding agents have reshaped software development, but the path to fully AI-native systems faces structural challenges.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs.
Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations.
arXiv:2606. 24151v1 Announce Type: cross Abstract: Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks.
arXiv:2604. 24222v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development relies on internal private libraries absent from public pre-training corpora.
arXiv:2606. 00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology.
Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies.