01.Agentic AI Defense: Decode-Time Provenance Binding for MCP

87% worth reading · novelty 1.9/3 ·new method ·cs.MA

02.The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows

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

03.Frontier-OPD: Discovering the Edge of Agent Capability and Teaching Agents to Go Beyond

81% worth reading · novelty 1.7/3 ·new method ·cs.CL

04.Every Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents

84% worth reading · novelty 1.5/3 ·applied system ·cs.CL

05.Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox

83% worth reading · novelty 1.4/3 ·benchmark/eval ·cs.CL

06.Toward an Agentic AI Approach to Public Health Data Collection

78% worth reading · novelty 1.8/3 ·applied system ·cs.MA

07.J-Comm: Jacobian-Guided Latent Communication between LLM Agents

75% worth reading · novelty 1.9/3 ·new method ·cs.CL

08.PULSES: multi-agent AI for autonomous excited-state model building and dynamics

74% worth reading · novelty 1.8/3 ·applied system ·cs.MA

09.Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems

76% worth reading · novelty 1.6/3 ·new method ·cs.MA

10.Markets of Minds: A 51-Billion-State Economy of Intelligence

71% worth reading · novelty 2.0/3 ·new method ·cs.MA

11.SemantEq: Faithful Bidirectional Equivalence of Formal Statements

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

12.KrishokTech: A Bengali Agricultural Advisory System with Explicit Authorization Controls

81% worth reading · novelty 1.2/3 ·applied system ·cs.CL

13.NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding

72% worth reading · novelty 1.8/3 ·new method ·cs.AI

14.Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations

73% worth reading · novelty 1.5/3 ·benchmark/eval ·cs.AI

15.Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation

71% worth reading · novelty 1.5/3 ·benchmark/eval ·cs.MA

16.SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning

58% worth reading · novelty 1.7/3 ·new method ·cs.AI

17.Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations

56% worth reading · novelty 1.7/3 ·benchmark/eval ·cs.AI

18.Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models

54% worth reading · novelty 1.8/3 ·new method ·cs.AI

19.Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora

59% worth reading · novelty 1.4/3 ·new method ·cs.CL

20.HGWM: Hierarchical Graph-Guided World Model for Zero-Shot Object Navigation via Graph Matching

63% worth reading · novelty 1.1/3 ·new method ·cs.MA