01. Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core

86% worth reading · novelty 1.9/3 · applied system · cs.MA

02. Simulated Control Evals

84% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

03. When Is a Memory Safe Enough to Act On? Action-Conditioned Verification for Long-Lived Agents

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

04. EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence

83% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

05. Can an Agent Debug a Web Corpus? Agentic Auditing of Slovak FineWeb2

81% worth reading · novelty 1.9/3 · applied system · cs.CL

06. Agri-SCHOLAR: Simulation-Grounded In-Season Rolling Advisories for Agricultural Crops Using LLM-Bounded Optimization

80% worth reading · novelty 1.9/3 · new method · cs.MA

07. Contestable Agents for Data Governance: Recording Human Stewardship of AI-Generated Metadata Across Structured and Unstructured Systems

83% worth reading · novelty 1.6/3 · applied system · cs.MA

08. ABRA: Agent-Bound UI for Human-Agent Communication beyond Chat with Reusable Views

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

09. Muffin - A Shared Memory Buffer for Asynchronous AI Agents

81% worth reading · novelty 1.8/3 · new method · cs.MA

10. Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure

79% worth reading · novelty 1.9/3 · applied system · cs.AI

11. Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash

81% worth reading · novelty 1.4/3 · applied system · cs.MA

12. LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades

76% worth reading · novelty 1.7/3 · benchmark/eval · cs.MA

13. Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity

70% worth reading · novelty 1.7/3 · new method · cs.MA

14. Consistent but Biased: Chair Personas Trade Noise for Bias in Multi-Agent Clinical Decisions

72% worth reading · novelty 1.5/3 · benchmark/eval · cs.MA

15. Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation

67% worth reading · novelty 1.8/3 · new method · cs.AI

16. Reliable AI-Assisted Decisions via Selective Auditing

69% worth reading · novelty 1.6/3 · new method · cs.LG

17. Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration

60% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

18. ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization

59% worth reading · novelty 1.8/3 · new method · cs.MA

19. Towards User Simulators That Stay On Task And Still Sound Natural

63% worth reading · novelty 1.5/3 · new method · cs.CL

20. When to Follow the Teacher: Advantage-Based On-Policy Distillation

52% worth reading · novelty 1.8/3 · new method · cs.AI