Search: “agents”

arXiv:2609.04495v1 Announce Type: new Abstract: We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection t

arXiv:2609.04034v1 Announce Type: cross Abstract: While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yield

arXiv:2609.03960v1 Announce Type: new Abstract: Banks need conversational systems that can answer product questions, assist customers with account-related requests, and operate safely within strict op

arXiv:2609.03797v1 Announce Type: new Abstract: Long-term human-AI interaction is difficult because the information that guides inference is updated implicitly by the model and is not directly inspect

arXiv:2609.02002v1 Announce Type: cross Abstract: Guideline-consistent semantic segmentation requires more than category recognition, as real-world labeling policies demand fine-grained, task-specific

arXiv:2609.02292v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: sele

arXiv:2609.02322v1 Announce Type: cross Abstract: The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at al

arXiv:2609.01814v1 Announce Type: new Abstract: Information sharing can improve a pooled estimate while eliminating independent rescue actions. This paper separates those effects in exact finite disco

arXiv:2609.00967v1 Announce Type: new Abstract: As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to us

arXiv:2609.00129v1 Announce Type: cross Abstract: The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near

arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic ac

arXiv:2408.12845v3 Announce Type: replace-cross Abstract: This paper considers a novel variant of the online fair division problem involving multiple agents in which a learner sequentially observes an

arXiv:2608.29460v1 Announce Type: new Abstract: When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legi

arXiv:2508.13073v3 Announce Type: replace-cross Abstract: Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional

arXiv:2608.30426v1 Announce Type: new Abstract: Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by ad

arXiv:2608.31100v1 Announce Type: new Abstract: Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent bench

arXiv:2608.28279v1 Announce Type: new Abstract: Multimodal lifelong navigation requires an agent to autonomously explore unseen environments while sequentially completing navigation tasks specified by

arXiv:2608.26480v1 Announce Type: cross Abstract: Multi-agent large language model systems are widely reported to beat single-model baselines, but the evidence is mixed, and comparisons are usually co

arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco

arXiv:1908.08773v3 Announce Type: replace Abstract: In certain reinforcement learning (RL) scenarios there are adversaries trying to interfere with the underlying reward process for their own benefit.

arXiv:2608.24804v1 Announce Type: new Abstract: We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include

arXiv:2608.21976v1 Announce Type: new Abstract: Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experiment

arXiv:2608.21500v1 Announce Type: cross Abstract: Prompt injection is listed as the #1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject

arXiv:2608.20481v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is an open source JSON-RPC protocol that standardizes how large language models (LLMs) interact with external systems

arXiv:2608.21332v1 Announce Type: new Abstract: Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce

arXiv:2606.18250v2 Announce Type: replace Abstract: Forecasting the evolution of dynamic environments is crucial for autonomous agents. While generative world models have achieved high photorealism in

arXiv:2608.21107v1 Announce Type: new Abstract: Large Language Models (LLMs) are moving from code completion toward repository-scale agents that retrieve context, edit files, execute tools, and partic

arXiv:2608.19854v1 Announce Type: cross Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture.

arXiv:2608.20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection. Harness optimization iteratively r

arXiv:2608.18704v1 Announce Type: cross Abstract: Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on

arXiv:2608.19073v1 Announce Type: new Abstract: An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a ro

arXiv:2608.19072v1 Announce Type: new Abstract: Large language model (LLM) agents can now post-train an LLM end-to-end. They can write code, launch training, evaluate checkpoints, and improve downstre

arXiv:2604.06474v2 Announce Type: replace Abstract: Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and analysi

arXiv:2608.17584v1 Announce Type: new Abstract: We propose HODAgent, a System-2 embodied agent for humanoid robots in service settings, addressing situated intent, responsive execution, task revision,

arXiv:2608.16033v1 Announce Type: new Abstract: In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent be

arXiv:2608.16590v1 Announce Type: new Abstract: Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in p

arXiv:2608.14085v1 Announce Type: new Abstract: Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors an

arXiv:2511.08001v3 Announce Type: replace Abstract: To facilitate effective, safe deployment in the real world, individual robots must reason about interactions with other agents, which often occur wi

arXiv:2608.13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices. These princip

arXiv:2608.14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applications that use large language models. A task may con

arXiv:2608.13684v1 Announce Type: new Abstract: This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence from embodied conversations and task demonstr

arXiv:2608.14441v1 Announce Type: new Abstract: Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions a

arXiv:2602.06746v2 Announce Type: replace Abstract: We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary,

arXiv:2608.14490v1 Announce Type: new Abstract: We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an executable world model for completing continual l

arXiv:2603.27803v2 Announce Type: replace Abstract: We provide a distributed online algorithm for multi-agent submodular maximization under communication delays. We are motivated by the future distrib

arXiv:2608.12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this mem