3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.09000v1 Announce Type: new Abstract: As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems, the integrity of loca…
arXiv:2610.09002v2 Announce Type: replace Abstract: When a team of agents shares a reward for completed tasks, reporting and stopping unsafe work reduces the team's reward.
arXiv:2610.09021v1 Announce Type: new Abstract: An agentic system issues several structurally different kinds of LLM calls.
arXiv:2610.09034v1 Announce Type: new Abstract: Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency.
arXiv:2610.09037v1 Announce Type: new Abstract: Supervisory governors can interfere with the tool-using agents they regulate.
arXiv:2610.09088v1 Announce Type: new Abstract: Agent checkpoint systems decide what state is recovery-relevant, how to snapshot it, and whether rollback is admissible.
arXiv:2610.09112v1 Announce Type: new Abstract: Before tool-using LLM agents are deployed in environmental and geospatial workflows, teams need evidence that an agent reliably selects the right operations against real AP…
arXiv:2610.09115v1 Announce Type: new Abstract: Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism.
arXiv:2610.09159v1 Announce Type: new Abstract: As autonomous coding agents get increasingly deployed, the risk that accidental or adversarially injected misspecifications in tasks lead to dangerous agent behavior is cri…
arXiv:2610.09193v1 Announce Type: new Abstract: MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting".
arXiv:2610.09237v1 Announce Type: new Abstract: Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models.
arXiv:2610.09294v1 Announce Type: new Abstract: Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments.
arXiv:2610.09335v1 Announce Type: new Abstract: Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability.
arXiv:2610.09374v1 Announce Type: new Abstract: Urban diagnosis integrates heterogeneous observations to identify urban problems, localize affected areas, and investigate contributing factors, informing evidence-based ur…
arXiv:2610.09377v1 Announce Type: new Abstract: Taxonomies are the symbolic representations through which AI systems organize evidence, aggregate patterns, and answer questions over large document collections.
arXiv:2610.09497v1 Announce Type: new Abstract: As AI agents work alongside humans in shared workspaces, a mutual awareness challenge arises: agents act at speeds that outpace human monitoring, and users' evolving intere…
arXiv:2610.09560v1 Announce Type: new Abstract: Long-horizon language agents often receive supervision only from terminal task outcomes, leaving little signal for distinguishing productive intermediate behavior from stag…
arXiv:2610.09590v1 Announce Type: new Abstract: Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely.
arXiv:2610.09624v1 Announce Type: new Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds directly remains poorly…
arXiv:2610.09667v1 Announce Type: new Abstract: Random selection is widely used in resource allocation and auditing, making reliable implementation essential for AI-agent systems.
arXiv:2610.09681v1 Announce Type: new Abstract: Program verification establishes software correctness through machine-checkable proofs constructed in theorem provers.
arXiv:2610.09856v1 Announce Type: new Abstract: Self-evolving tool-integrated agents learn from tasks and feedback generated within their own training loop.
arXiv:2610.09872v1 Announce Type: new Abstract: Evaluating agents by outcomes alone can obscure the capabilities that produce them.
arXiv:2610.09890v1 Announce Type: new Abstract: Inverse optimization estimates the weights of an objective function that explain observed decisions as optimal solutions, and is used in a variety of fields.
arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime.
arXiv:2610.09973v1 Announce Type: new Abstract: When the harmfulness of an LLM agent's output can be quantified, a natural jailbreaking objective is to maximize expected harmfulness over admissible input modifications.
arXiv:2610.10062v1 Announce Type: new Abstract: Tool-using agents are usually scored on whether they finish a task while the tools work.
arXiv:2610.10071v1 Announce Type: new Abstract: LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces.
arXiv:2610.10120v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction…
arXiv:2610.10184v1 Announce Type: new Abstract: Developing optimization models for production scheduling requires substantial expert effort.
arXiv:2610.10256v1 Announce Type: new Abstract: Reality may establish that an outcome occurred without identifying which evolving procedure produced it or why.
arXiv:2610.10285v1 Announce Type: new Abstract: In the wake of the increasingly public discussion about AI alignment, recent work has tried to propose specific AI architectures that behave safely.
arXiv:2610.10407v1 Announce Type: new Abstract: As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention.
arXiv:2610.10478v1 Announce Type: new Abstract: How can we predict which base checkpoint is worth an expensive round of agentic post-training?
arXiv:2610.10513v1 Announce Type: new Abstract: Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a langua…
arXiv:2610.08812v1 Announce Type: cross Abstract: We present Go2-DrivoR, a goal-conditioned adaptation of the end-to-end autonomous driving trajectory planning framework DrivoR for urban navigation with quadrupedal robot…
arXiv:2610.08871v1 Announce Type: cross Abstract: Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to…
arXiv:2610.08928v1 Announce Type: cross Abstract: LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retrai…
arXiv:2610.08933v1 Announce Type: cross Abstract: Deep-space crews cannot rely on real-time ground support for urgent off-nominal events.
arXiv:2610.08954v1 Announce Type: cross Abstract: Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames.
arXiv:2610.09138v1 Announce Type: cross Abstract: Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid, low-rate, and benign-looking while the population…
arXiv:2610.09163v1 Announce Type: cross Abstract: Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhibit non-c…
arXiv:2610.09240v1 Announce Type: cross Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions.
arXiv:2610.09264v1 Announce Type: cross Abstract: Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security…
arXiv:2610.09285v1 Announce Type: cross Abstract: Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior.
arXiv:2610.09469v1 Announce Type: cross Abstract: Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observing graphical interfaces and issuing commands such…
arXiv:2610.09581v1 Announce Type: cross Abstract: Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which preserved record supports that finding.
arXiv:2610.09643v1 Announce Type: cross Abstract: Drug discovery for neurological disease has traditionally centered on the molecules altered by disease.
arXiv:2610.09772v2 Announce Type: replace-cross Abstract: Edge language-model agents must hold a persona and reason correctly at once, in one context window that fills with history and persona instructions.
arXiv:2610.09858v1 Announce Type: cross Abstract: Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment.