01. Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

86% worth reading · novelty 1.9/3 · new method · cs.AI

02. CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

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

03. RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

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

04. FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA

86% worth reading · novelty 1.8/3 · new method · cs.MA

05. Loopjacking: Hijacking Human-in-the-Loop Approval

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

06. AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory

82% worth reading · novelty 1.8/3 · new method · cs.AI

07. Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents

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

08. Available Guardrails: Certifying Selective Prediction across ML Systems

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

09. NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities

85% worth reading · novelty 1.4/3 · new method · cs.AI

10. When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence

80% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

11. TrialAtlas: Multi-Agent Research Organization for Clinical Trial Design and Optimization

80% worth reading · novelty 1.7/3 · applied system · cs.CL

12. Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw

77% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

13. SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes

76% worth reading · novelty 1.9/3 · benchmark/eval · cs.MA

14. An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency

74% worth reading · novelty 2.0/3 · new method · cs.CL

15. Language-model groups overstate consensus when replaying human deliberation on a reasoning task

75% worth reading · novelty 1.7/3 · benchmark/eval · cs.MA

16. LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents

76% worth reading · novelty 1.4/3 · new method · cs.MA

17. Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions

80% worth reading · novelty 1.0/3 · benchmark/eval · cs.MA

18. Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention

64% worth reading · novelty 1.9/3 · new method · cs.CL

19. What Should We Ask Next? Retrieval-Aware Question Learning under Partial Evidence

65% worth reading · novelty 1.7/3 · new method · cs.AI

20. Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition

65% worth reading · novelty 1.5/3 · benchmark/eval · cs.AI