Search: “agents”

arXiv:2606.02388v1 Announce Type: cross Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little superv

arXiv:2505.19489v2 Announce Type: replace Abstract: The Linux kernel is a critical system, serving as the foundation for numerous systems. Bugs in the Linux kernel can cause serious consequences, affe

arXiv:2606.00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems lev

arXiv:2605.30907v1 Announce Type: cross Abstract: We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet wo

arXiv:2605.30686v1 Announce Type: cross Abstract: ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, a

arXiv:2605.30712v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scr

arXiv:2605.29668v1 Announce Type: new Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the

arXiv:2605.29559v1 Announce Type: new Abstract: Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. Howe

arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. Thi

arXiv:2605.30256v1 Announce Type: cross Abstract: Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonve

arXiv:2605.28114v1 Announce Type: new Abstract: As autonomous AI agents are deployed in persistent, interacting networks -- coordinating tasks, routing resources, and accumulating reputational histori

arXiv:2605.28046v1 Announce Type: new Abstract: Existing agent memory systems universally follow what we term a Memory-as-Tool paradigm where a single query triggers one-shot retrieval of flat passage

arXiv:2406.03474v2 Announce Type: replace Abstract: Language-guided autonomous driving requires bridging a large abstraction gap between high-level natural-language instructions and low-level vehicle

arXiv:2605.27240v1 Announce Type: new Abstract: Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to us

arXiv:2602.22190v2 Announce Type: replace-cross Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a

arXiv:2605.26177v1 Announce Type: cross Abstract: Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on e

arXiv:2605.24183v1 Announce Type: cross Abstract: We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through latent world recovery. AvalancheBench improves on existing benc

arXiv:2605.25624v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its exte

arXiv:2605.25632v1 Announce Type: new Abstract: Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuari

arXiv:2602.02474v2 Announce Type: replace-cross Abstract: Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixe

arXiv:2605.23949v1 Announce Type: cross Abstract: As Large Language Models (LLMs) evolve into interactive agents, understanding their behavioral alignment within human social dynamics becomes essentia

arXiv:2605.23950v1 Announce Type: new Abstract: This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely

arXiv:2602.11243v2 Announce Type: replace-cross Abstract: Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augm

arXiv:2604.05157v2 Announce Type: replace Abstract: Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evalu

arXiv:2605.22855v1 Announce Type: cross Abstract: Personalized pricing negotiations are a challenging testbed for LLM agents because successful interaction does not guarantee profitable decision makin

arXiv:2602.11210v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on

arXiv:2605.22148v1 Announce Type: cross Abstract: Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation

arXiv:2605.20530v1 Announce Type: cross Abstract: Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evalu

arXiv:2605.20246v1 Announce Type: new Abstract: Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple

arXiv:2605.20477v1 Announce Type: cross Abstract: Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task

arXiv:2605.20306v1 Announce Type: new Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous

arXiv:2605.19484v1 Announce Type: cross Abstract: While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workfl

arXiv:2603.11768v2 Announce Type: replace Abstract: Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong m

arXiv:2605.19192v1 Announce Type: new Abstract: Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or trans

arXiv:2605.19127v1 Announce Type: new Abstract: LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what m

arXiv:2605.17583v1 Announce Type: new Abstract: While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the

arXiv:2605.17933v1 Announce Type: new Abstract: Vision-language model (VLM) agents increasingly rely on memory-augmented reinforcement learning to reuse experience across long-horizon tasks, yet most

arXiv:2605.16679v1 Announce Type: cross Abstract: End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions

arXiv:2506.16042v2 Announce Type: replace Abstract: Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused sole

arXiv:2605.16883v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail t

arXiv:2605.17637v1 Announce Type: new Abstract: Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate tr

arXiv:2605.15281v1 Announce Type: cross Abstract: Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entir

arXiv:2605.15669v1 Announce Type: new Abstract: Manufacturable chip layouts must satisfy thousands of geometry-based design rules, and design rule checking (DRC) enforces them by running executable DR

arXiv:2605.14084v1 Announce Type: cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these cap

arXiv:2605.14865v1 Announce Type: new Abstract: AI agents execute complex multi-step processes, but current evaluation falls short: outcome metrics report success or failure without explaining why, an

arXiv:2605.14678v1 Announce Type: new Abstract: The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life a