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.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

03.Simulated Control Evals

83% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.AI

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

82% worth reading · novelty 1.9/3 ·applied system ·cs.CL

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

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

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

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

07.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

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

82% worth reading · novelty 1.7/3 ·applied system ·cs.MA

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

81% worth reading · novelty 1.7/3 ·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.LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades

78% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.MA

12.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

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

69% worth reading · novelty 1.9/3 ·new method ·cs.AI

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

70% worth reading · novelty 1.8/3 ·new method ·cs.MA

15.Reliable AI-Assisted Decisions via Selective Auditing

70% worth reading · novelty 1.6/3 ·new method ·cs.LG

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

71% worth reading · novelty 1.5/3 ·benchmark/eval ·cs.MA

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

61% worth reading · novelty 2.0/3 ·benchmark/eval ·cs.AI

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

65% worth reading · novelty 1.5/3 ·new method ·cs.CL

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

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

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

53% worth reading · novelty 1.8/3 ·new method ·cs.AI