arXiv:2608. 01042v1 Announce Type: cross Abstract: Enterprise AI agents act across many apps whose data changes continuously, so an answer is correct only relative to what data existed and who could see it at the moment it was asked.
arXiv:2608. 03764v1 Announce Type: new Abstract: Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively.
arXiv:2606. 05684v1 Announce Type: new Abstract: A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions.
arXiv:2607. 11149v1 Announce Type: new Abstract: LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces.
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:2606. 07299v1 Announce Type: new Abstract: Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, verify sources, and synthesize long-form reports.
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments.
arXiv:2608. 14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons.
arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.
arXiv:2608. 14270v1 Announce Type: new Abstract: Time series analysis in high-stakes domains relies on recurring data releases, where new observations can alter the evidence base and the validity of later conclusions.
arXiv:2606. 00619v1 Announce Type: cross Abstract: Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows.
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.
LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint.