01. Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems

84% worth reading · novelty 2.0/3 · benchmark/eval · cs.MA

02. How Do Hardware Faults Manifest Differently in LLM Agents?

85% worth reading · novelty 1.8/3 · benchmark/eval · cs.MA

03. X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems

86% worth reading · novelty 1.7/3 · new method · cs.AI

04. RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics

86% worth reading · novelty 1.5/3 · new method · cs.AI

05. JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models

80% worth reading · novelty 1.8/3 · new method · cs.MA

06. Ask Your Advisor: Learning When to Consult Stronger Models in Agentic Systems

85% worth reading · novelty 1.5/3 · new method · cs.MA

07. SwingGuard: Risk-Conditioned Multi-Agent Swing Trading with Dual-Timescale Governance

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

08. Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing

75% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

09. A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models

78% worth reading · novelty 1.6/3 · new method · cs.MA

10. Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga

65% worth reading · novelty 2.5/3 · applied system · cs.AI

11. RSI-Anything: Unlocking Recursive Self-Improvement with World Models

76% worth reading · novelty 1.7/3 · new method · cs.CL

12. MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents

77% worth reading · novelty 1.6/3 · benchmark/eval · cs.AI

13. Structural Automata for Neural Semantic Parsing

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

14. OpenSocialJax: Evaluating Social Adaptation in Sequential Social Dilemmas with Open-Ended Environmental Dynamics

77% worth reading · novelty 1.5/3 · benchmark/eval · cs.MA

15. A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning

71% worth reading · novelty 1.9/3 · new method · cs.CL

16. Returning to Development States: When Full Sandbox Snapshots Help Coding Agents

78% worth reading · novelty 1.3/3 · new method · cs.LG

17. QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code

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

18. Can Language Models Play the Wikipedia Game?

71% worth reading · novelty 1.2/3 · benchmark/eval · cs.AI

19. OccludeBench: Can VLMs Find What's Missing?

57% worth reading · novelty 1.8/3 · benchmark/eval · cs.CL

20. Specialists Learn Faster: Knowledge Organization in Pre-training Shapes Knowledge Update Efficiency

53% worth reading · novelty 2.0/3 · new method · cs.LG