← Back to all news
arXiv AI

REALM: Identifying Minimal Task Assets for LLM Agents

REALM (Required Execution Assets Linked to a Mission) is a method for identifying and managing the minimal set of assets that a large language model (LLM) agent needs to complete a task, even when those assets are discovered only during execution. It represents required assets as nodes in a dependency graph, separates asset discovery from authorization, and uses a REALM Builder to maintain grants and a Partial API Manager to expose resource‑bound APIs within a task container. In experiments on 60 clean tasks and 560 injected cases, REALM achieved 40.0% task completion and reduced attack success rate from 16.6% to 0.2% when using qwen3.5‑flash as the base model.

Related stories

arXiv AI
Sep 25

Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery

The paper introduces skilder, a framework that organizes LLM agent capabilities into role‑scoped bundles of skills, tools, and instructions, with explicit limits. Agents start with a minimal role catalog, discover the roles needed for a task, and receive the associated tools only through a single MCP server, ensuring deterministic enforcement of scope. Experiments on 13 tasks with six models show that skilder’s authorization layer prevents unauthorized tool calls and parameter violations while maintaining flexibility through dynamic cross‑role capability acquisition.

By Michael Stettler, Benjamin Girardet, Jonas Canton, Nicolas Corod
llmsagents
More like this →
arXiv AI
Aug 18

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

arXiv:2608. 15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.

By Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo, Yinghao Yu, Yizhou Shan, Bo Li, Binhang Yuan, Wei Wang
llmsagentsbenchmarks
More like this →
arXiv AI
Oct 19

Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias

The paper investigates how the representation of tool interfaces—referred to as a tool schema—affects the performance of large language model agents. By systematically transforming a native tool schema with nine operators, the authors demonstrate that agents exhibit significant variability in success rates across different but functionally equivalent schema variants, a phenomenon they call schema bias. Experiments on eleven LLMs, including closed models, reveal that success can range from complete failure to 97% solely due to schema differences, and that training only mitigates bias when the specific variant is included in the training data.

By Yinhong Liu, Zhili Tan, Zilin Wang, Zhijiang Guo
llmsagentssafety
More like this →
arXiv AI
Oct 21

Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment

The paper introduces AuthorizationBench, a benchmark designed to evaluate whether large language model (LLM) agents act within the scope of user authorization when acting on their behalf. The benchmark comprises 286 executable tasks across ten application domains, covering situational triggers, presence or absence of direct harmful consequences, and varying reasoning effort. In experiments with four models and multiple agent harnesses, agents violated authorization in 19.2% of trajectories, with rates ranging from 10.5% to 26.6% across configurations, and increased reasoning effort did not substantially reduce these violations.

By Zhiping Zhang, Franklin Mingzhe Li, Zihao Huang, Tianshi Li
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Jun 9

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

arXiv:2606. 09730v1 Announce Type: new Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite.

By Pu Ning, Quan Chen, Kun Tao, Xinyu Tang, Tianshu Wang, Qianggang Cao, Xinyu Kong, Zujie Wen, Zhiqiang Zhang, Jun Zhou
llmsagentsfine-tuning
More like this →
arXiv AI
Aug 28

Five Primitives for Governing Autonomous AI Agents at Runtime

The paper proposes five runtime primitives—discovery, identity, governance, attestation, and supply chain—to manage autonomous AI agents in enterprise settings. It argues that traditional control models fail because agents are transient, model-driven, and self‑discoverable, making runtime governance essential. The authors detail an implementation that mediates agent actions against policy, authorizes them via a per‑tenant vocabulary, and records them in a verifiable ledger, noting the associated operational costs and partial deployment status.

By Jiten Oswal, John Cadeddu
agentssafety
More like this →
arXiv AI
Aug 13

VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

arXiv:2608. 12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation.

By Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder, Siyu Huo, Raavi Gupta, Abhinav Jain, Praveen Venkateswaran, Abdulhamid Adebayo, Danish Contractor
agentsbenchmarks
More like this →