← cd ..

$ cat ./papers/2026-10-04.json

// 2026-10-04 · generated 4 Oct 2026

// ranked against: "LLM agents, tool use, and structured/typed model outputs"

// categories: cs.AI, cs.CL, cs.LG, cs.MA

← 2026-10-03 latest ↑ 2026-10-05 →

01. KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

88% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

02. Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows

86% worth reading · novelty 2.0/3 · benchmark/eval · cs.CL

03. Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models

87% worth reading · novelty 1.7/3 · benchmark/eval · cs.CL

04. VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

85% worth reading · novelty 1.8/3 · new method · cs.MA

05. ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

83% worth reading · novelty 1.9/3 · new method · cs.MA

06. From Knowledge Access to Source Learning: Developing Source-Specific Competence

82% worth reading · novelty 1.9/3 · new method · cs.AI

07. AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents

85% worth reading · novelty 1.6/3 · new method · cs.CL

08. Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

82% worth reading · novelty 1.8/3 · new method · cs.AI

09. LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing

82% worth reading · novelty 1.8/3 · applied system · cs.MA

10. HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols

79% worth reading · novelty 1.9/3 · new method · cs.MA

11. LLM2Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them

83% worth reading · novelty 1.6/3 · new method · cs.CL

12. Managing Context and Communication in Distributed Agentic UAV Swarms

81% worth reading · novelty 1.6/3 · new method · cs.MA

13. SoK: Decentralized Agent Economic Infrastructure

74% worth reading · novelty 1.9/3 · survey/position · cs.MA

14. VISTA: A Visual Harness for Reasoning in an Interactive World

77% worth reading · novelty 1.7/3 · new method · cs.AI

15. Can AI Scientists Coordinate at Runtime?

77% worth reading · novelty 1.6/3 · new method · cs.MA

16. ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

74% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

17. Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

67% worth reading · novelty 1.9/3 · new method · cs.MA

18. Form and Void: Entangled Composition through an Autonomous AI Agent

72% worth reading · novelty 1.4/3 · new method · cs.MA

19. A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance

78% worth reading · novelty 0.9/3 · applied system · cs.MA

20. DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

66% worth reading · novelty 1.6/3 · new method · cs.AI