01. Agent-Editing World Model: Rethinking World Modeling for LLM Agents

85% worth reading · novelty 1.9/3 · new method · cs.AI

02. Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation

84% worth reading · novelty 1.8/3 · new method · cs.MA

03. Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer

82% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

04. Shutdown Sabotage Propensities in Multi-Agent Systems

80% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

05. Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences

77% worth reading · novelty 2.0/3 · new method · cs.MA

06. KITE: Scaling Jev Population Experiments with Sparse Flagship Calibration

76% worth reading · novelty 2.0/3 · new method · cs.MA

07. Agent Name Collision Attacks in Multi-Agent Systems

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

08. Agent-based Modeling: Equilibrium, Echo Chambers, and Efficiency in Hybrid Coevolutionary Opinion Games

71% worth reading · novelty 1.8/3 · new method · cs.MA

09. From Intents to Algorithms: Verified Algorithm Discovery for Transport Networks

69% worth reading · novelty 1.7/3 · new method · cs.MA

10. Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark

66% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

11. StudentBench: AI and human tutoring yield equivalent GRE learning gains

64% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

12. Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance

58% worth reading · novelty 2.0/3 · new method · cs.MA

13. Multi-Agent AI Architecture for Regulated Insurers: A generic AI framework under Solvency II and the AI Act in Austria and Germany

61% worth reading · novelty 1.6/3 · new method · cs.MA

14. Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction

56% worth reading · novelty 1.9/3 · new method · cs.AI

15. AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios

59% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

16. Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings

47% worth reading · novelty 2.2/3 · benchmark/eval · cs.CL

17. MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

57% worth reading · novelty 1.5/3 · new method · cs.AI

18. An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice

52% worth reading · novelty 1.6/3 · benchmark/eval · cs.AI

19. Learning the Cost of Reliable Inference

50% worth reading · novelty 1.8/3 · new method · cs.AI

20. Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning

49% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI