{"total":18,"rows":[{"id":"2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","created":"2026-04-09","cited_by_count":74,"area":"agents"},{"id":"2601.14192","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","created":"2026-01-20","cited_by_count":16,"area":"agents"},{"id":"2606.06284","title":"ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents","created":"2026-06-04","cited_by_count":9,"area":"agents"},{"id":"2606.13884","title":"Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents","created":"2026-06-11","cited_by_count":6,"area":"agents"},{"id":"2606.07904","title":"Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents","created":"2026-06-05","cited_by_count":5,"area":"agents"},{"id":"2606.15508","title":"ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents","created":"2026-06-13","cited_by_count":5,"area":"agents"},{"id":"2607.07321","title":"From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents","created":"2026-07-08","cited_by_count":4,"area":"agents"},{"id":"2603.21354","title":"The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project","created":"2026-03-22","cited_by_count":1,"area":"agents"},{"id":"2606.17519","title":"Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery","created":"2026-06-16","cited_by_count":1,"area":"agents"},{"id":"2607.10569","title":"When Does Restricting a Coding Agent to execute_code Help? A Regime $\\times$ Agent-Design Ablation","created":"2026-07-12","cited_by_count":1,"area":"agents"},{"id":"2607.25853","title":"HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2607.11126","title":"ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.13396","title":"Set-shifting Behavioral Test for Harnessed Agents","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.14108","title":"Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2608.10037","title":"DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2609.02035","title":"Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.23512","title":"AgentBetta: Verification-Driven Adaptive Configuration of an AI Nano-Agent through Selective Expansion and Verified Contraction","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.39989","title":"What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}