arXiv:2606. 06698v1 Announce Type: new Abstract: Production agentic systems routinely face evolving constraints and must comply from the very next interaction.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2608. 06216v1 Announce Type: cross Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.
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.
arXiv:2607. 08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures.
arXiv:2607. 21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user.
arXiv:2609. 18366v1 Announce Type: new Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed target agent.
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.