← cd ..

$ cat ./papers/2026-10-31.json

// 2026-10-31 · generated 31 Oct 2026

// ranked against: "LLM agents, tool use, and structured/typed model outputs"

// categories: cs.AI, cs.CL, cs.LG, cs.MA

← 2026-10-30latest ↑2026-11-01 →

01.Testimony from Timelines: Evidence-Grounded Significance Testing of Temporal Clinical Hypotheses

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

02.PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication

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

03.Gym-Anything for Robotics: Scaling physical simulations with digital agents

80% worth reading · novelty 2.1/3 ·benchmark/eval ·cs.AI

04.Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering

84% worth reading · novelty 1.8/3 ·new method ·cs.MA

05.Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs

82% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.CL

06.VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

84% worth reading · novelty 1.7/3 ·new method ·cs.AI

07.Advancing Clinical Genomic Analysis with a Skill-Centred Agent

84% worth reading · novelty 1.6/3 ·applied system ·cs.AI

08.Cinematize from Unreal: Agentic Choreography for Controllable World Simulation

82% worth reading · novelty 1.7/3 ·applied system ·cs.MA

09.MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

81% worth reading · novelty 1.8/3 ·new method ·cs.MA

10.Routed Continual Learning

80% worth reading · novelty 1.8/3 ·new method ·cs.MA

11.ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender

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

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

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

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

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

14.Learning Calibrated Confidence for Multi-Agent Collaboration

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

15.EpiAgent: Epistemic Self-Play for LLM Agents

74% worth reading · novelty 1.8/3 ·new method ·cs.MA

16.Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In

76% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.AI

17.From extreme weather to agricultural consequences with agentic AI

68% worth reading · novelty 1.9/3 ·applied system ·cs.AI

18.FARMS: A Verifiable Foundation for Automated Computational Science

68% worth reading · novelty 1.9/3 ·applied system ·cs.AI

19.Sticky Collusion: Persistence of LLM Agent Collusion after Incentive Removal and Partner Replacement

72% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.MA

20.Long-Term Agent Memory through Complementary Curation and Consolidation

79% worth reading · novelty 1.0/3 ·new method ·cs.MA