Search: “agents”

arXiv:2609.03546v1 Announce Type: new Abstract: We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution, self-reproduction, and self-organization on any s

arXiv:2609.03416v1 Announce Type: new Abstract: LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capabili

arXiv:2512.10534v4 Announce Type: replace Abstract: Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even solve International Mathematical Olympiad (IMO)

arXiv:2609.00795v1 Announce Type: cross Abstract: Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that

arXiv:2609.00683v1 Announce Type: new Abstract: Creative generation tasks, such as narrative writing and scientific ideation, demand both high-quality outputs and distinct responses across independent

arXiv:2609.01360v1 Announce Type: new Abstract: Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually ident

arXiv:2609.00643v1 Announce Type: new Abstract: Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version cor

arXiv:2609.00814v1 Announce Type: new Abstract: Remote sensing visual models have continuously advanced various interpretation tasks. However, the research process behind model improvement still heavi

arXiv:2608.29228v1 Announce Type: new Abstract: Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution

arXiv:2602.13671v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works oft

arXiv:2601.21545v2 Announce Type: replace Abstract: Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constra

arXiv:2608.28266v1 Announce Type: new Abstract: Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still la

arXiv:2608.26117v1 Announce Type: cross Abstract: RDBMS (Relational Database Management System) databases face several limitations, including slow execution with multi-hop queries and a lack of explai

arXiv:2608.25457v2 Announce Type: replace-cross Abstract: Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain se

arXiv:2608.26563v1 Announce Type: new Abstract: Agentic (tool-using) language models are mainly trained on tool-call traces and agent trajectories during post-training. These data provide direct behav

arXiv:2608.24361v1 Announce Type: new Abstract: Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing ef

arXiv:2608.24076v1 Announce Type: new Abstract: Evaluation of agentic information retrieval remains limited to scripted interactions with uniform users, missing both natural personality diversity and

arXiv:2608.24048v1 Announce Type: cross Abstract: While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Exist

arXiv:2608.23623v1 Announce Type: cross Abstract: Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, bu

arXiv:2608.23395v1 Announce Type: cross Abstract: Recent LLM-agent systems make conflicting design bets: decompose work across many narrow agents, or use one strong tool-using agent. This pilot studie

arXiv:2608.20851v1 Announce Type: cross Abstract: Agentic engineering systems have shown strong performance on general-purpose benchmarks, yet their effectiveness in enterprise resource planning (ERP)

arXiv:2608.17148v1 Announce Type: cross Abstract: A personal language agent learns a fact from one audience and may later place it in the prompt it assembles for another. This memory-to-context step i

arXiv:2511.15239v3 Announce Type: replace Abstract: In decentralized multi-agent navigation, agents that independently compute their controls without communicating goals or intentions can fall into sy

arXiv:2511.17006v2 Announce Type: replace Abstract: Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in

arXiv:2608.14074v1 Announce Type: new Abstract: AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructu

arXiv:2608.12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities,

arXiv:2608.13046v1 Announce Type: new Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-age

arXiv:2608.12629v1 Announce Type: new Abstract: GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compil

arXiv:2608.12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology

arXiv:2608.09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate soci

arXiv:2608.10689v1 Announce Type: cross Abstract: Terminal interfaces to conversational agents report rich internal state (listening, thinking, executing tools, awaiting input, failing) almost entirel

arXiv:2608.08045v1 Announce Type: new Abstract: Urban embodied intelligence requires coordination among heterogeneous agents (e.g., UAVs, ground robots, and autonomous vehicles) in dynamic cities. Sim

arXiv:2608.06922v1 Announce Type: new Abstract: Negotiation is a demanding social task for LLM agents, requiring strategic reasoning, persuasion, and interpersonal adaptation. Yet existing benchmarks

arXiv:2608.07167v1 Announce Type: new Abstract: Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it should

arXiv:2608.06702v1 Announce Type: cross Abstract: Lifelong Multi-Agent Path Finding (LMAPF) requires generating collision-free paths for large agent fleets under strict real-time constraints. Reactive

arXiv:2608.06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits

arXiv:2608.05729v1 Announce Type: new Abstract: As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems

arXiv:2608.04056v1 Announce Type: new Abstract: When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP sys

arXiv:2608.03609v1 Announce Type: new Abstract: Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data.

arXiv:2608.02986v1 Announce Type: cross Abstract: A software agent on a public blockchain accumulates authority and economic stakes, raising the engineering question of what makes it count as an indiv

arXiv:2607.17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current eva

arXiv:2608.01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that su

arXiv:2607.28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the

arXiv:2607.28685v1 Announce Type: new Abstract: Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, I

arXiv:2607.28595v1 Announce Type: new Abstract: The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather tha

arXiv:2607.26588v1 Announce Type: new Abstract: The rapid development of large language models (LLMs) has renewed interest in agent-based modeling (ABM). However, current LLM-based ABM research faces