arXiv AI
Jun 24
LemonHarness Technical Report
arXiv:2606. 24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration.
SkillEffect: Checked Lowering for Memory-Bounded Agent Tools
arXiv:2608. 17007v1 Announce Type: new Abstract: Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs.
Related stories
arXiv Machine Learning
Jul 14
ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
arXiv:2607. 11126v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools served by shared providers and accessed by heterogeneous downstream agents.
Hugging Face Trending Papers
Jun 2
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited. This paper presents Agent libOS, a library-OS-inspired runtime substrate for LLM agents.
arXiv AI
Aug 5
TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.
arXiv AI
Jul 15
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
arXiv AI
Jun 3
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
arXiv:2606. 03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited.
arXiv AI
Jun 9
SecureClaw: Clawing Back Control of LLM Agents
arXiv:2606. 09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene.
arXiv AI
23h ago
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
arXiv:2608. 17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation.
arXiv AI
Jun 2
Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
arXiv:2606. 00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology.
arXiv AI
Jun 3
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
arXiv:2602. 12430v4 Announce Type: replace-cross Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice.
arXiv AI
Jul 29
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
arXiv AI
Jun 29
On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models
arXiv:2606. 27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken.