01.Agentic World Modeling for Agent Test-time Scaling without Environment Replica

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

02.RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory

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

03.How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

86% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.CL

04.AI evaluators favor job applications written by certain AI models, independent of candidate quality

80% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.MA

05.TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents

81% worth reading · novelty 1.8/3 ·benchmark/eval ·cs.AI

06.Completeness and Cost of Retrieval Structures for Multi-Tool Requests in LLM Agents

86% worth reading · novelty 1.4/3 ·benchmark/eval ·cs.CL

07.Flide: Accelerating Decision Inference with Exact State Forking

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

08.Collaborative AI agents for autonomous experimental research with solid-state quantum spins

77% worth reading · novelty 1.9/3 ·applied system ·cs.MA

09.MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

78% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.MA

10.Learning Calibrated Confidence for Multi-Agent Collaboration

83% worth reading · novelty 1.5/3 ·new method ·cs.MA

11.EpiAgent: Epistemic Self-Play for LLM Agents

76% worth reading · novelty 1.9/3 ·new method ·cs.MA

12.ORION: An Outcome-Driven LLM Advisor for RL-Based Multi-Domain 6G Slice Placement

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

13.When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents

66% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.MA

14.Understanding LLM-Based Bargaining of Driving Agents in Mixed-Autonomy Traffic

67% worth reading · novelty 1.9/3 ·new method ·cs.MA

15.Subquadratic Attention with a Hierarchical Tree-Structured Indexer

66% worth reading · novelty 1.9/3 ·new method ·cs.AI

16.Renegotiable Options Fail to Prevent Hold-Up Between Two Profit-Maximizing Frontier LLM Agents

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

17.Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

61% worth reading · novelty 1.5/3 ·new method ·cs.AI

18.PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users

60% worth reading · novelty 1.5/3 ·benchmark/eval ·cs.CL

19.The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results

54% worth reading · novelty 1.6/3 ·new method ·cs.AI

20.Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice

57% worth reading · novelty 1.4/3 ·benchmark/eval ·cs.AI