01. CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling

85% worth reading · novelty 2.0/3 · new method · cs.AI

02. Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System

83% worth reading · novelty 2.0/3 · benchmark/eval · cs.MA

03. Recursive Video In-Context Learning for Agentic Robot

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

04. One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline

85% worth reading · novelty 1.8/3 · new method · cs.AI

05. Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification

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

06. BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents

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

07. Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help

82% worth reading · novelty 1.8/3 · survey/position · cs.MA

08. TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts

75% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

09. T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search

86% worth reading · novelty 1.2/3 · new method · cs.CL

10. PlotGround: Grounding Plot Digitization in Real Scientific Figures and Their Source Data

78% worth reading · novelty 1.7/3 · benchmark/eval · cs.CL

11. MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents

78% worth reading · novelty 1.7/3 · new method · cs.AI

12. Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation

72% worth reading · novelty 1.9/3 · benchmark/eval · cs.MA

13. MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks

75% worth reading · novelty 1.6/3 · new method · cs.CL

14. Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement

74% worth reading · novelty 1.4/3 · new method · cs.MA

15. IdeaLens: Detecting AI Ideas in Long-form Writing

65% worth reading · novelty 2.0/3 · new method · cs.CL

16. Symmetry and AI-assisted discovery of magic-state factories

65% worth reading · novelty 2.0/3 · new method · cs.MA

17. Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce

61% worth reading · novelty 1.9/3 · new method · cs.MA

18. Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs

66% worth reading · novelty 1.5/3 · new method · cs.CL

19. ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring

66% worth reading · novelty 1.0/3 · applied system · cs.CL

20. Base Models Can Reason By Taking a Cue From Training Data

51% worth reading · novelty 1.9/3 · new method · cs.AI