01. NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents

83% worth reading · novelty 2.1/3 · benchmark/eval · cs.AI

02. Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation

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

03. WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness

86% worth reading · novelty 1.8/3 · benchmark/eval · cs.MA

04. Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents

86% worth reading · novelty 1.8/3 · benchmark/eval · cs.CL

05. Evaluator-in-the-Loop Monte Carlo Tree Search via LLM Agents for Motif Scaffolding in Protein Design

83% worth reading · novelty 1.9/3 · new method · cs.MA

06. Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents

85% worth reading · novelty 1.7/3 · new method · cs.AI

07. EdgeAgent: Orchestrating On-Device LLM inference for End-User Multi-Agent Systems on CPU-GPU Unified Memory Architectures

78% worth reading · novelty 1.9/3 · new method · cs.MA

08. FinNextAssist: Towards Professional Financial Deep Research Assistant

86% worth reading · novelty 1.3/3 · new method · cs.MA

09. 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

78% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

10. Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise

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

11. Dynamic Expert Pruning for Multi-Agent Systems

76% worth reading · novelty 1.8/3 · new method · cs.MA

12. FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs

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

13. A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control

74% worth reading · novelty 1.7/3 · benchmark/eval · cs.CL

14. FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

73% worth reading · novelty 1.7/3 · new method · cs.AI

15. Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows

82% worth reading · novelty 1.0/3 · benchmark/eval · cs.MA

16. Defense-in-Depth at the Perception-Reasoning Interface of LLM-Centric Agentic UAV Swarms

76% worth reading · novelty 1.4/3 · applied system · cs.MA

17. Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents

70% worth reading · novelty 1.8/3 · benchmark/eval · cs.MA

18. Language Models that Play Chess and Explain Their Moves

64% worth reading · novelty 2.0/3 · new method · cs.CL

19. What Should World Models Forget? Stratified Retention for Continual Adaptation

54% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

20. Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System

64% worth reading · novelty 1.2/3 · benchmark/eval · cs.AI