Search: “tool-use”

arXiv:2607.02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an answer was produced. In safety-critical

arXiv:2605.11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often con

arXiv:2606.08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action t

arXiv:2605.28532v1 Announce Type: new Abstract: Tool-using agents often incur substantial computational cost due to long reasoning chains and iterative tool usage. In practical scenarios, many tasks b

arXiv:2605.11026v1 Announce Type: cross Abstract: Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks

arXiv:2604.22820v1 Announce Type: cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibil

arXiv:2512.22673v3 Announce Type: replace Abstract: Travel planning is a natural real-world task to test large language models' (LLMs) planning and tool-use abilities. Although prior work has studied

arXiv:2604.16706v1 Announce Type: cross Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated a

arXiv:2604.10352v1 Announce Type: new Abstract: Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, c

arXiv:2609.05441v1 Announce Type: new Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dial

arXiv:2608.29942v1 Announce Type: cross Abstract: The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized actio

arXiv:2608.30704v1 Announce Type: new Abstract: AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perf

arXiv:2606.31648v1 Announce Type: new Abstract: We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterp

arXiv:2605.09934v1 Announce Type: new Abstract: Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, a

arXiv:2601.03555v2 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.

arXiv:2610.15488v1 Announce Type: cross Abstract: Formulaic alpha mining seeks interpretable expressions that rank assets by future returns. The task is challenging because it demands simultaneous pro

arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and

arXiv:2607.10198v2 Announce Type: replace Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these int

arXiv:2608.20381v1 Announce Type: cross Abstract: Automating slide editing requires simultaneously satisfying modification accuracy, preservation fidelity, and robustness to deck length. Existing LLM-

arXiv:2608.13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols.

arXiv:2601.00086v3 Announce Type: replace Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or

arXiv:2606.31392v1 Announce Type: new Abstract: Tool-augmented vision-language models (VLMs) can solve multimodal, multi-step tasks by calling external tools, yet they remain fragile in practice. Exis

arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca

arXiv:2604.15231v2 Announce Type: replace Abstract: Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (

arXiv:2606.00566v1 Announce Type: cross Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party con

arXiv:2605.27820v1 Announce Type: new Abstract: As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop

arXiv:2605.18548v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalida

arXiv:2605.13228v1 Announce Type: cross Abstract: Video understanding requires active evidence seeking, motivating tool-augmented video agents for temporal reasoning, cross-modal understanding, and co

arXiv:2609.36829v1 Announce Type: new Abstract: An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability wh

arXiv:2609.36138v1 Announce Type: new Abstract: Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarification, answering directly, or d

arXiv:2609.28693v1 Announce Type: new Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal to

arXiv:2609.14780v1 Announce Type: cross Abstract: Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that

arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student

arXiv:2608.30362v1 Announce Type: new Abstract: As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Succes

arXiv:2608.10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), to

arXiv:2608.04436v1 Announce Type: new Abstract: Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understandi

arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe

arXiv:2607.07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that th

arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments

arXiv:2605.18748v1 Announce Type: new Abstract: Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and ref

arXiv:2506.08332v3 Announce Type: replace Abstract: Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows

arXiv:2604.12116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks

arXiv:2511.09572v2 Announce Type: replace Abstract: For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environment

arXiv:2608.29128v1 Announce Type: new Abstract: Tool-using agents are commonly evaluated by a single bit: whether an end-to-end workflow completed. This metric fails to distinguish failures that matte

arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing e

arXiv:2512.21414v2 Announce Type: replace Abstract: Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tool