Search: “tool-use”

arXiv:2605.09734v1 Announce Type: cross Abstract: Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use

arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we

arXiv:2508.08791v3 Announce Type: replace Abstract: Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of eff

arXiv:2609.37453v1 Announce Type: new Abstract: When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per

arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W

arXiv:2608.22339v1 Announce Type: new Abstract: Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents. Prevailing agent self-evolution para

arXiv:2607.05775v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and ope

arXiv:2607.05780v1 Announce Type: cross Abstract: While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to nove

arXiv:2607.01465v1 Announce Type: new Abstract: Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means

arXiv:2511.02734v3 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability

arXiv:2606.26403v1 Announce Type: new Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longi

arXiv:2606.23937v1 Announce Type: cross Abstract: Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test t

arXiv:2605.09730v1 Announce Type: new Abstract: Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structur

arXiv:2608.01056v1 Announce Type: cross Abstract: Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments,

arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing

arXiv:2609.28003v1 Announce Type: new Abstract: Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment

arXiv:2608.26189v1 Announce Type: new Abstract: Tool-using agents fail two ways: choosing the wrong tool, or forming wrong arguments, and an early failure of either kind can silently corrupt everythin

arXiv:2607.29190v1 Announce Type: new Abstract: Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates gener

arXiv:2606.25819v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benc

arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetti

arXiv:2610.07753v1 Announce Type: cross Abstract: Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence es

arXiv:2610.01349v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusa

arXiv:2609.15011v1 Announce Type: new Abstract: Memory-augmented and tool-using agents expose exact private values when remote LLMs process retrieved memory, tool actions, and intermediate observation

arXiv:2608.23623v1 Announce Type: cross Abstract: Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, bu

arXiv:2608.02698v1 Announce Type: cross Abstract: Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrast

arXiv:2606.09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently, jailbreak

arXiv:2603.14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reason

arXiv:2605.26542v1 Announce Type: cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterp

arXiv:2605.16909v1 Announce Type: new Abstract: Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate

arXiv:2604.07960v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon reasoning and coherent modeling actions. Large Language Models (LLMs)

arXiv:2609.37475v1 Announce Type: new Abstract: Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this p

arXiv:2609.37315v1 Announce Type: cross Abstract: Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool call

arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowi

arXiv:2607.10490v2 Announce Type: replace-cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages

arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and

arXiv:2601.15322v3 Announce Type: replace-cross Abstract: Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Har

arXiv:2609.17985v1 Announce Type: new Abstract: AI agents are usually evaluated by whether they complete a task. In interactive service settings, a successful agent can still frustrate users by asking

arXiv:2609.03236v1 Announce Type: new Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment

arXiv:2608.11110v1 Announce Type: new Abstract: When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compa

arXiv:2607.19356v1 Announce Type: new Abstract: Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility a

arXiv:2607.07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive

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