Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2609.36488v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong performance on complex web navigation tasks, yet they remain brittle in real-world settings...
arXiv:2609.36820v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing...
arXiv:2609.36843v1 Announce Type: new Abstract: Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World m...
arXiv:2609.37432v1 Announce Type: new Abstract: Looped reasoning models repeatedly apply a shared set of parameters, enabling more computation without increasing the model size. These models also sup...
arXiv:2609.38133v1 Announce Type: new Abstract: Generative modeling is widely used for producing diverse objects from complex, multimodal distributions. However, its expressivity does not, in general...
arXiv:2609.35930v1 Announce Type: cross Abstract: Consider a community of agents who are seeking consensus on a set of parameters. The agents agree to use the same Bregman-type divergence to quantify...
arXiv:2609.36012v1 Announce Type: cross Abstract: General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (IC...
arXiv:2609.37599v1 Announce Type: cross Abstract: Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators...
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a...
arXiv:2602.15382v3 Announce Type: replace-cross Abstract: Heterogeneous multi-agent systems combine models with different capabilities through a common communication interface. Exchanging internal st...
arXiv:2606.08729v2 Announce Type: replace-cross Abstract: Developing navigation policies requires simulation scenarios that support repeatable training and evaluation. Despite the availability of num...
arXiv:2609.03221v3 Announce Type: replace-cross Abstract: Counterfactual fairness audits of clinical language-model agents report a flip rate: how often an action changes when only the patient's demo...
arXiv:2609.36246v1 Announce Type: new Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressivel...
arXiv:2609.36344v1 Announce Type: new Abstract: Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis. However, they m...
arXiv:2609.36675v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize extern...
arXiv:2609.36691v1 Announce Type: new Abstract: Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embod...
arXiv:2609.36722v1 Announce Type: new Abstract: Large language model (LLM) agents repeatedly load reusable content, such as skills, documents, and memory entries, into the current context. Re-encodin...
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,...
arXiv:2609.37017v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natu...
arXiv:2609.36987v1 Announce Type: new Abstract: Graph databases are increasingly queried through natural language, yet every existing benchmark evaluates isolated single-turn queries rather than the...