Knowledge catalogue
arXiv:2610.07898v1 Announce Type: new Abstract: Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt t
arXiv:2610.07851v1 Announce Type: new Abstract: Agentic workflows enable large language models (LLMs) to solve complex tasks by coordinating reasoning, tool use, and verification. However, a workflow
arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored
arXiv:2610.08170v1 Announce Type: cross Abstract: Agentic VLM pipelines increasingly pass the same static visual evidence through multiple specialist agents and tools. This design creates an orchestra
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data
arXiv:2610.06514v1 Announce Type: cross Abstract: The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within
arXiv:2610.05572v1 Announce Type: new Abstract: Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report st
arXiv:2610.04087v1 Announce Type: new Abstract: Agentic workflows are increasingly used across domains such as technology, finance, and enterprise operations. As these agents become more widely deploy
arXiv:2610.05563v1 Announce Type: cross Abstract: Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for
arXiv:2610.04914v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current
arXiv:2603.27170v2 Announce Type: replace Abstract: Relative camera pose is a basic geometric cue for visual re-localization and scene understanding. When using images alone, visual evidence may not s
arXiv:2610.05151v1 Announce Type: new Abstract: Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive se
arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their exte
arXiv:2610.03226v1 Announce Type: cross Abstract: GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal ho
arXiv:2610.02762v1 Announce Type: new Abstract: Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We analyze six commercial r
arXiv:2610.03574v1 Announce Type: new Abstract: We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13
arXiv:2610.02670v1 Announce Type: cross Abstract: LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to exec
arXiv:2610.02627v1 Announce Type: new Abstract: An email assistant should not complete less work simply because a user phrases the same request differently. Yet most benchmarks test each task with onl
arXiv:2610.02740v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental
arXiv:2610.03519v1 Announce Type: new Abstract: A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers
arXiv:2610.02717v1 Announce Type: new Abstract: A key challenge in bringing embodied intelligence into the real world is transferring capabilities from simulation to reality and enabling agents to con
arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt
arXiv:2610.02994v1 Announce Type: cross Abstract: LLM agents often fail mid-task due to invalid tool calls, repeated actions, or poorly grounded reasoning, and learning from these failures is a path t
arXiv:2610.03585v1 Announce Type: cross Abstract: Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare d
arXiv:2610.03057v1 Announce Type: new Abstract: Relational foundation models are increasingly pretrained on synthetic databases, yet downstream benchmarks reveal little about why one synthetic corpus
arXiv:2601.11354v2 Announce Type: replace Abstract: Recent LLM-for-Space systems address mission planning, scheduling, operations support, simulator control, and autonomy, but their evaluations use di
arXiv:2610.01166v1 Announce Type: cross Abstract: Cardiovascular magnetic resonance (CMR), including cine imaging, is a reference standard for the noninvasive assessment of cardiac morphology and vent
arXiv:2610.02206v1 Announce Type: cross Abstract: LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existi
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source h
arXiv:2610.00282v1 Announce Type: new Abstract: How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting,
arXiv:2610.02181v1 Announce Type: new Abstract: We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native
arXiv:2602.13691v2 Announce Type: replace Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However,
arXiv:2610.00354v1 Announce Type: cross Abstract: AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of def
arXiv:2508.08882v5 Announce Type: replace Abstract: Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-int
arXiv:2610.01249v1 Announce Type: new Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffect
arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific A
arXiv:2610.00704v1 Announce Type: new Abstract: Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating
arXiv:2610.00041v1 Announce Type: cross Abstract: Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We meas
Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can
arXiv:2603.17343v3 Announce Type: replace Abstract: The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditiona
arXiv:2609.39022v1 Announce Type: cross Abstract: Coding agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expe
arXiv:2609.38923v1 Announce Type: new Abstract: Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with
arXiv:2609.39601v1 Announce Type: cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fa
arXiv:2609.38974v1 Announce Type: new Abstract: Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-le
arXiv:2609.39363v1 Announce Type: cross Abstract: Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed acro
arXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send
arXiv:2609.40027v1 Announce Type: new Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed act
arXiv:2609.40325v1 Announce Type: new Abstract: As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomal
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,
arXiv:2602.18998v2 Announce Type: replace Abstract: LLM agents are increasingly expected to operate as general-purpose systems that resolve real-world user requests, yet their dynamic scaling behavior
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a c
arXiv:2609.33772v2 Announce Type: replace Abstract: Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executable
arXiv:2609.34683v1 Announce Type: new Abstract: The optimization of LLM serving engines, such as vLLM and SGLang, is largely benchmark-driven: optimizations, scheduling policies, hardware and system d
arXiv:2609.33882v1 Announce Type: new Abstract: Glove-based motion capture is emerging as a scalable approach to collecting dexterous-hand demonstration data. However, due to the kinematic gap between
arXiv:2609.31632v1 Announce Type: new Abstract: Electroencephalography (EEG) analysis is evolving from short-segment classification toward long-horizon interpretation that demands iterative evidence a
arXiv:2609.31789v1 Announce Type: cross Abstract: In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investiga
arXiv:2609.35479v1 Announce Type: new Abstract: The ability to design a tool for a task marks a level of intelligence beyond merely understanding, selecting, or using one. Existing methods for robotic
arXiv:2609.30297v1 Announce Type: cross Abstract: Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr
arXiv:2609.31418v1 Announce Type: new Abstract: A photorealistic 3D view tells a teleoperator where a robot is, but not what the scene contains, how well each object has been observed, or how to turn