01. Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization

87% worth reading · novelty 2.0/3 · benchmark/eval · cs.CL

02. Evolving Agent Interfaces

86% worth reading · novelty 2.1/3 · new method · cs.AI

03. Cache Engineering for Agents

84% worth reading · novelty 1.9/3 · new method · cs.CL

04. Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation

81% worth reading · novelty 2.0/3 · new method · cs.AI

05. OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long-Term Personal Assistants

84% worth reading · novelty 1.8/3 · benchmark/eval · cs.CL

06. Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration

81% worth reading · novelty 1.9/3 · new method · cs.MA

07. Proof-Carrying Contracts: Commitments AI Agents Cannot Break

79% worth reading · novelty 2.0/3 · new method · cs.MA

08. Semantic Observability for Autonomous Systems Diagnostics

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

09. Autonomous intelligence for mining productivity: a multi-agent AI approach to operational value creation

78% worth reading · novelty 1.8/3 · new method · cs.MA

10. GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery

77% worth reading · novelty 1.9/3 · new method · cs.AI

11. SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images

80% worth reading · novelty 1.6/3 · new method · cs.AI

12. Does Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control Settings

81% worth reading · novelty 1.4/3 · benchmark/eval · cs.MA

13. Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks

73% worth reading · novelty 1.9/3 · new method · cs.CL

14. Discovery-Probability Graph Planning for Embodied Agents in Tasks with Hidden Cooperation Requirements

72% worth reading · novelty 1.9/3 · new method · cs.MA

15. S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents

71% worth reading · novelty 1.8/3 · applied system · cs.MA

16. Evolving Semantic Indexes for Generative Retrieval

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

17. Claims of emergence in AI should be grounded in information decomposition

70% worth reading · novelty 1.8/3 · survey/position · cs.MA

18. UniWALM: Unified World Action Language Model for Embodied Robot Control

60% worth reading · novelty 2.0/3 · new method · cs.AI

19. GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models

64% worth reading · novelty 1.7/3 · new method · cs.CL

20. Value-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated Debates

59% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI