arXiv:2606. 06090v1 Announce Type: new Abstract: LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade.
arXiv:2606. 11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts.
arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
arXiv:2606. 06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
arXiv:2607. 13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents.
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: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.
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
arXiv:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
arXiv:2607. 13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations.
Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query.