Search: “agents”

arXiv:2610.21218v1 Announce Type: new Abstract: Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observati

arXiv:2610.20786v1 Announce Type: new Abstract: Multi-modal agents have made significant progress in interacting with open worlds. However, their ability to self-evolve remains limited. Supervised fin

arXiv:2610.22289v1 Announce Type: new Abstract: Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves

arXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions

arXiv:2610.20003v2 Announce Type: replace Abstract: Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investiga

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 inform

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 i

arXiv:2610.17837v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation t

arXiv:2610.20457v1 Announce Type: new Abstract: Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences. Natural-language scientific claims, wri

arXiv:2610.15481v1 Announce Type: new Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agen

arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weight

arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly assoc

arXiv:2610.16238v1 Announce Type: new Abstract: LLM agents increasingly control robots using VLA policies, perception models, and procedural knowledge. These modules are difficult to reuse because the

arXiv:2610.13021v1 Announce Type: new Abstract: Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, exist

arXiv:2610.13000v1 Announce Type: new Abstract: Language-model agents are used for specialized work such as financial research, healthcare and law. Such agents are often capable enough for a task but

arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized re

arXiv:2610.12975v1 Announce Type: new Abstract: We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents agains

arXiv:2607.09996v2 Announce Type: replace Abstract: Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler

arXiv:2610.12374v1 Announce Type: new Abstract: Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice

arXiv:2610.10610v1 Announce Type: cross Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor

arXiv:2610.11707v1 Announce Type: new Abstract: Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new t

arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using avai

arXiv:2610.11647v1 Announce Type: cross Abstract: Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from inde

arXiv:2610.11464v1 Announce Type: new Abstract: We changed the agent: did it actually get better? Every self-improving agent loop answers this hundreds of times, and every answer comes from a verifier

arXiv:2610.10426v1 Announce Type: new Abstract: Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existi

arXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester

arXiv:2610.08076v1 Announce Type: new Abstract: Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertin

arXiv:2610.05195v1 Announce Type: new Abstract: The next generation of multimodal research agents must reason over long-lived research histories rather than short model completions. During a single ta

arXiv:2610.02488v1 Announce Type: new Abstract: Language-model agents increasingly rely on harnesses that manage bounded context, persistent memory, tools, verification, and repeated execution, yet ex

arXiv:2610.03315v1 Announce Type: new Abstract: Trajectory evaluation is essential for improving the reliability of LLM-based agents, but production use makes it expensive to run repeatedly. Modern ag

arXiv:2610.00854v1 Announce Type: new Abstract: Frontier vision-language models (VLMs) combine scene estimation, interaction grounding, and executable actions. Understanding how these abilities suppor

arXiv:2610.02122v1 Announce Type: cross Abstract: Real-world enterprise data science and analytics workflows require reasoning across dozens of tables, performing statistical analyses, and acting on t

arXiv:2610.01045v1 Announce Type: new Abstract: A chatbot that says 'I will remind you tomorrow' will not run again until the user writes. We call such a promise an empty commitment: a promise of an a

arXiv:2610.00354v1 Announce Type: cross Abstract: AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of def

arXiv:2610.00041v1 Announce Type: cross Abstract: Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We meas

arXiv:2609.39607v1 Announce Type: cross Abstract: Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and C

arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their cont

arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorith

arXiv:2609.35936v1 Announce Type: cross Abstract: As autonomous systems and embodied intelligence enter the dynamic physical world, multi-agent collaboration calls for a paradigm shift in communicatio

arXiv:2609.37267v1 Announce Type: new Abstract: Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or

arXiv:2609.37539v1 Announce Type: new Abstract: Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in

arXiv:2609.37950v1 Announce Type: new Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However,

arXiv:2505.06191v2 Announce Type: replace-cross Abstract: This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent

arXiv:2609.33762v1 Announce Type: cross Abstract: LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing

arXiv:2604.04247v2 Announce Type: replace Abstract: Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without paramete

arXiv:2604.14590v3 Announce Type: replace-cross Abstract: In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI a