Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitatio...
arXiv:2610.17288v1 Announce Type: new Abstract: Building physical simulations from video requires coding agents to translate observations into executable models and refine them through tool use. We i...
arXiv:2610.17893v1 Announce Type: new Abstract: Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing informati...
arXiv:2610.18090v1 Announce Type: new Abstract: Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these infor...
arXiv:2610.15725v2 Announce Type: cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to una...
arXiv:2610.16297v1 Announce Type: cross Abstract: Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests wh...
arXiv:2610.16778v1 Announce Type: cross Abstract: Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII)....
arXiv:2610.18262v1 Announce Type: cross Abstract: Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such...
arXiv:2605.26911v2 Announce Type: replace Abstract: LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and...
arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search...
arXiv:2610.04561v2 Announce Type: replace Abstract: Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across...
arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, thes...
arXiv:2603.26515v2 Announce Type: replace-cross Abstract: Efficient and robust turn-taking detection remains a significant challenge in industrial-grade voice AI agents. Existing systems often rely o...
arXiv:2608.11242v2 Announce Type: replace-cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We study Side Constraints (SCs), user...
arXiv:2609.35557v2 Announce Type: replace-cross Abstract: The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property. The ha...
arXiv:2610.19614v1 Announce Type: new Abstract: In this work, we reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations. We show that success...
arXiv:2610.18948v1 Announce Type: cross Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize...
arXiv:2610.19951v1 Announce Type: cross Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while jud...
arXiv:2610.20293v1 Announce Type: cross Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the result...
arXiv:2603.18965v2 Announce Type: replace Abstract: Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by pr...