Search: “agents”

arXiv:2609.31430v1 Announce Type: new Abstract: Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compressio

arXiv:2609.30940v1 Announce Type: new Abstract: Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial dec

arXiv:2609.30325v1 Announce Type: new Abstract: Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a

arXiv:2609.28843v1 Announce Type: cross Abstract: Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonom

arXiv:2609.28475v1 Announce Type: new Abstract: Forecasting agents increasingly combine language-model reasoning, retrieval, ensembling, and calibration, but it remains unclear when each behavior shou

arXiv:2609.27307v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents enable the fulfillment of complex user instructions through multi-turn interactions with software environments, re

arXiv:2609.23363v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led to the emergence of coding agents capable of performing complex engineering tasks, including re

arXiv:2605.12481v2 Announce Type: replace Abstract: Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operat

arXiv:2609.22247v1 Announce Type: new Abstract: Search agents are usually trained under a single harness. But once an agent is deployed in a real application, its harness is frequently updated (e.g.,

arXiv:2609.22308v1 Announce Type: new Abstract: Coding-agent benchmarks usually evaluate implementation after the target behavior has been specified in text, code, or demonstrations. Existing research

arXiv:2609.23215v1 Announce Type: new Abstract: LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs an

arXiv:2605.06445v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production

arXiv:2609.21562v1 Announce Type: cross Abstract: Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game

arXiv:2609.19892v1 Announce Type: cross Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing

arXiv:2510.25595v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by

arXiv:2609.20715v1 Announce Type: cross Abstract: Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored acti

arXiv:2609.19947v1 Announce Type: new Abstract: LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local t

arXiv:2609.18045v1 Announce Type: new Abstract: Recovering latent interaction structures from multi-agent dynamics is important for understanding and predicting interacting systems. Trajectory-based s

arXiv:2609.16302v1 Announce Type: cross Abstract: When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and

arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect promp

arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent ga

arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply o

arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through ru

arXiv:2609.13076v1 Announce Type: cross Abstract: Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end

arXiv:2609.10922v1 Announce Type: new Abstract: Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this p

arXiv:2609.09853v1 Announce Type: new Abstract: LLM agents for enterprise systems of record cannot be evaluated on customer production data, and no existing substitute provides ground truth. We presen

arXiv:2609.07603v1 Announce Type: new Abstract: Financial scenarios are diverse and complex, spanning varying data conditions, tool configurations, and workflows. Yet existing CUA, Computer-Using Agen

arXiv:2609.09153v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions throug

arXiv:2609.07255v1 Announce Type: new Abstract: Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how ski

arXiv:2609.05224v1 Announce Type: new Abstract: Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in their potential to act as autonomous agents for real-wo

arXiv:2609.02309v1 Announce Type: new Abstract: GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task succ

arXiv:2609.02246v1 Announce Type: new Abstract: Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is i

arXiv:2609.01487v1 Announce Type: cross Abstract: Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable chann

arXiv:2609.01245v1 Announce Type: cross Abstract: Reinforcement learning is a natural way to post-train LLM agents for long-horizon interactive tasks judged only by end-of-task verification, yet a sha

arXiv:2609.00859v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced opti

arXiv:2607.15550v2 Announce Type: replace Abstract: Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safe

arXiv:2609.00549v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps.

arXiv:2609.00568v1 Announce Type: cross Abstract: Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement o

arXiv:2609.01056v1 Announce Type: new Abstract: Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, per

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:2601.16690v2 Announce Type: replace Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather than

arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengin

arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal,

arXiv:2608.27831v1 Announce Type: cross Abstract: Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, an

arXiv:2608.26372v1 Announce Type: cross Abstract: Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and dep

arXiv:2608.26432v1 Announce Type: cross Abstract: Voice agents must call tools and hold multi-turn dialogue entirely through speech, yet the dominant paradigm trains them in text. Existing frameworks