Coverage, Not Credit: Failure-Credit Routing of Zeroth-Order Perturbation Budget

arXiv:2608.28475v1 Announce Type: new Abstract: When a multi-agent system changes its team, it also changes the messages and final answer it produces, so an end-to-end accuracy

arXiv:2609.04518v1 Announce Type: new Abstract: Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices:

arXiv:2608.27507v1 Announce Type: cross Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently

arXiv:2605.05657v1 Announce Type: new Abstract: Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the

arXiv:2609.29007v1 Announce Type: new Abstract: Tool-using agents are continually updated with new interaction data. After each policy update, however, previously estimated action

arXiv:2605.11603v1 Announce Type: new Abstract: The growing deployment of large language models (LLMs) makes per-request routing essential for balancing response quality and

arXiv:2610.02808v1 Announce Type: new Abstract: Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog,

arXiv:2609.29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We