Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2610.14495v1 Announce Type: new Abstract: Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation. We ar...
arXiv:2610.14774v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool...
arXiv:2610.14790v1 Announce Type: new Abstract: Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy sele...
arXiv:2605.28918v2 Announce Type: replace-cross Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed a...
arXiv:2610.15046v1 Announce Type: new Abstract: Beliefs in a Partially Observable Markov Decision Process (POMDP) are posterior distributions over the hidden state given the agent's history of action...
arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is...
arXiv:2610.15292v1 Announce Type: new Abstract: LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retri...
arXiv:2610.15298v1 Announce Type: new Abstract: Large language models (LLMs) offer a new approach to wearable-sensor-based human activity recognition. Retrieval-augmented generation (RAG) further int...
arXiv:2607.10526v5 Announce Type: replace Abstract: Self-improving personal agents write profiles, memories, and reusable skills that carry over from one chat to the next. Prior works ask whether a m...
arXiv:2610.14547v2 Announce Type: cross Abstract: To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but...
arXiv:2610.14766v1 Announce Type: cross Abstract: AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark,...
arXiv:2610.15221v1 Announce Type: new Abstract: AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, whil...
arXiv:2610.14960v1 Announce Type: cross Abstract: Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst? Do they adopt the same strategy, and can agents scale to rea...
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this...
arXiv:2610.15244v1 Announce Type: cross Abstract: Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to...
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in a...
arXiv:2610.17419v1 Announce Type: cross Abstract: Autonomous quadrotor flight in cluttered environment is an key capability for tasks like inspection and search. Navigation policies trained in simula...
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protoc...
arXiv:2610.16288v2 Announce Type: new Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents....
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily...