50 articles mentioning Agents-A1-Q4_K_M-GGUF
arXiv:2610.28425v1 Announce Type: cross Abstract: Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent without user input. A one-time indirect prompt injection committed to either chann
arXiv:2610.28484v1 Announce Type: new Abstract: AI agents increasingly act on behalf of people or other agents, purchasing services, exchanging information and delegating work. What an agent must respect is written in instructions, policies or agreements, but text alone cannot make it comply. It may
arXiv:2610.27290v1 Announce Type: new Abstract: Test-case generation is critical but remains challenging for language models. Existing test-time scaling methods either isolate candidates or aggregate traces, which do not scale to long-horizon tasks. We present TEX, a collaborative test-time scaling
arXiv:2610.28361v1 Announce Type: new Abstract: Long-horizon deep search requires LLM agents to iteratively decompose complex information needs, gather evidence from external sources, and maintain a reliable research state under multiple constraints. A central challenge is that early mistakes can be
arXiv:2610.27495v1 Announce Type: cross Abstract: Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solutions or verifier-derived rewards. We introduce Retrospective Self-Distillation
arXiv:2610.27032v1 Announce Type: new Abstract: Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, particularly in environments without prior training. A key limitation of single LLMs
arXiv:2606.28235v2 Announce Type: replace-cross Abstract: In July 2026, about 1,200 AI agents in an internal OpenAI evaluation, meant to run in isolation, used a shared package server as a message board, and about 700 of them joined an attack on Hugging Face. An automated scorer judged each agent on
arXiv:2610.27981v1 Announce Type: new Abstract: Reasoning-enabled language model agents can incur substantial computation before acting, although the reasoning needed varies across decisions. Existing stopping signals, such as confidence and intermediate-answer stability, can vary in effectiveness a
arXiv:2610.17710v2 Announce Type: replace Abstract: Training graphical user interface (GUI) agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Process rewards offer a promising direction for credit assignment to intermediate actions; however, acc
arXiv:2609.33848v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model--environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learn
arXiv:2610.27581v1 Announce Type: new Abstract: Full-duplex speech agents must update persistent memory while listening and speaking, yet it remains unclear which events should be stored, revised, or excluded. Existing benchmarks isolate interaction timing from memory outcomes, obscuring the state t
arXiv:2610.27954v1 Announce Type: new Abstract: Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile in long-horizon settings, where errors accumulate and
arXiv:2606.27806v4 Announce Type: replace Abstract: Language agents, such as ReAct, Reflexion, and RAP, implicitly predict how the world will change as they plan and act, using imagined state transitions to guide their decisions. These predictions are encoded in the agents' backbone LLMs as internal
arXiv:2610.26995v1 Announce Type: new Abstract: LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic retrieval treats skills as i
arXiv:2607.01767v3 Announce Type: replace Abstract: Long-horizon language agents make interdependent decisions across multiple rounds, forming growing planning graphs in which later decisions depend on earlier states, observations, and tool outputs. Errors in these graphs can therefore propagate thr
arXiv:2608.21755v2 Announce Type: replace Abstract: Long-horizon agents require more than retrieval over stored conversations: they must preserve source evidence, revise outdated knowledge, and distinguish relevant memories from sufficient support for an answer. We present ECHO (Embodied Context & H
arXiv:2610.17544v2 Announce Type: replace-cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and errors until its facts change, then quietly answers wrong. Mos
arXiv:2610.26955v1 Announce Type: new Abstract: Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states. Although effective, many belief-state methods encode memory in discrete natural language, where repeat
arXiv:2610.28381v1 Announce Type: cross Abstract: Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels: (1) an action-level dataset
arXiv:2610.27046v1 Announce Type: new Abstract: As AI systems begin to resolve open research problems, reliable verification becomes increasingly important. Formal mathematics provides a trusted framework for mathematical reasoning, enabling agents to produce machine-checkable proofs while conductin
arXiv:2610.26941v1 Announce Type: new Abstract: Large language models (LLMs) are enabling agents to move beyond predefined workflows toward autonomous planning and execution, creating new opportunities for smart manufacturing. However, dynamic environments, complex physical constraints, and stringen
arXiv:2610.26887v1 Announce Type: new Abstract: Large language model (LLM) agents are evolving from conversational assistants into Cowork Agents capable of autonomous planning, tool use, and complex task execution. Financial analysis requires these agents to integrate cross-document evidence and per
arXiv:2610.27435v1 Announce Type: new Abstract: Long-horizon terminal agents may solve a task in one run yet fail across repeated runs. Stochastic errors can propagate through actions and context, creating a gap between capability and reliable execution. We present RiseHarness, a framework for itera
arXiv:2610.27524v1 Announce Type: new Abstract: Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolving, so it remains unclear how memory systems organize it and thereby affect code ag
arXiv:2610.27645v1 Announce Type: new Abstract: As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading failures in subsequent actions. Reliable error detection and recovery have become c
arXiv:2610.27655v1 Announce Type: new Abstract: Multi-agent systems (MAS) built from language models are deployed on the premise that collaboration beats a single-agent system (SAS), yet when it pays is unclear. The most systematic study to date gives a capability-saturation rule: coordination helps
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a l
arXiv:2602.02589v2 Announce Type: replace Abstract: Large language model (LLM) evaluation commonly relies on fixed human-authored benchmarks or centralized human/model judges. Fixed benchmarks can age and enter model training corpora, while centralized judges introduce their own scoring preferences.
arXiv:2610.26659v2 Announce Type: replace-cross Abstract: Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering offers limited evidence of whether models can co
arXiv:2610.27115v1 Announce Type: new Abstract: LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed action without tracking whether its content comes from the user or from external sour
arXiv:2610.22732v1 Announce Type: new Abstract: Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and ma
arXiv:2610.23254v1 Announce Type: new Abstract: Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every fail
arXiv:2609.34971v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong performance on tool-use agentic tasks when given a fixed tool schema. Yet a tool schema is not the action space of an agent; it is merely one interface representation of it. The same executable action
arXiv:2610.22987v1 Announce Type: new Abstract: Coding agents use execution harnesses to constrain the consequences of prompt injection by enforcing permission boundaries. These systems deterministically intercept any out-of-sandbox action and prompt the user for approval. To reduce approval fatigue
arXiv:2610.23251v1 Announce Type: new Abstract: Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this need, we introduce FLARE (Feeder-Level Agent Restoration Evaluation), a physics-gro
arXiv:2610.22953v1 Announce Type: new Abstract: Domain terminology provides concise descriptions of game states and strategic relationships, but whether game-playing language models can accurately recognize these concepts and relate them to move evaluation remains unclear. We construct a controlled
arXiv:2610.21711v1 Announce Type: cross Abstract: Repeated Bertrand competition is a stringent benchmark for algorithmic pricing: in homogeneous-goods markets, standard learning procedures typically select the stage-game Nash outcome with prices near marginal cost. We show that LLM pricing agents ca
arXiv:2607.03162v3 Announce Type: replace Abstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy interaction histories, and select among competing alternatives. Existing
arXiv:2610.23071v1 Announce Type: new Abstract: Large language models increasingly act as agents that call external tools, yet most tool-safety research examines only what follows a tool call. The prior decision of whether to call the tool remains largely unexamined and can influence downstream safe
arXiv:2609.39717v2 Announce Type: replace Abstract: Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority during a consequential task. We propose a Runtime Assurance Contract (RAC), a policy-level forma
arXiv:2610.04184v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or
arXiv:2606.24893v2 Announce Type: replace Abstract: For agents to learn continuously from interaction with the world at test time, they must be able to explore effectively, acquire new world knowledge and skills, retain relevant episodic experiences, and plan over long horizons. To evaluate these ke
arXiv:2610.23266v1 Announce Type: cross Abstract: LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redundant or jointly necessary evidence. We study per-decision memory sufficiency: sele
arXiv:2610.22469v1 Announce Type: new Abstract: LLM-based agents are increasingly credited with the competences of practical reasoning: planning, monitoring, and correcting their own actions. Their success is attributed to the prompting strategies and agent architectures built around the model, such
arXiv:2610.23317v1 Announce Type: new Abstract: Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without an explicit representation of this knowledge, an agent may produce incorrect an
arXiv:2610.11773v3 Announce Type: replace Abstract: Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue th
arXiv:2503.18238v4 Announce Type: replace-cross Abstract: We examined the mechanisms underlying productivity and performance gains from AI agents using a large-scale experiment on Pairit, a platform we developed to study human-AI collaboration. We randomly assigned 2,234 participants to human-human
arXiv:2610.23554v1 Announce Type: new Abstract: Large language model agents increasingly rely on skills to extend their capabilities in complex tasks. However, scalable skill use requires Selective Skill Exposure (SSE): providing relevant procedural content when needed while avoiding unnecessary exp
arXiv:2610.23342v1 Announce Type: new Abstract: Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics remain fixed,
arXiv:2610.22684v1 Announce Type: cross Abstract: Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) forecasters often begins with preassembled evidence at a single prediction