arXiv:2604. 03588v3 Announce Type: replace Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 20245v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context learning ability, enabling them to incorporate external information provided in the input prompt.
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.
arXiv:2608. 13921v1 Announce Type: new Abstract: LLM agents increasingly maintain personal memory across sessions, but it can conflict.
arXiv:2607. 04617v1 Announce Type: new Abstract: Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window.
arXiv:2607. 16716v1 Announce Type: new Abstract: Large language models and LLM-based agents are widely used as personal chat assistants, enterprise copilots, and autonomous workflow agents.
arXiv:2606. 24976v1 Announce Type: cross Abstract: Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories.