← cd ..

$ cat ./papers/2026-10-01.json

// 2026-10-01 · generated 1 Oct 2026

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

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

← 2026-09-30 latest ↑ 2026-10-02 →

01. PhantomEnvironments: Training LLM Agents in Fictional Worlds

83% worth reading · novelty 2.0/3 · new method · cs.CL

02. Cogentic: Multi-Agent Orchestration for Automated Proof Discovery

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

03. Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

86% worth reading · novelty 1.6/3 · new method · cs.MA

04. PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

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

05. OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation

81% worth reading · novelty 1.9/3 · new method · cs.MA

06. RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement

83% worth reading · novelty 1.7/3 · new method · cs.MA

07. Turbo Harness: Instance-Adaptive Harness Optimization

83% worth reading · novelty 1.7/3 · new method · cs.AI

08. AIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISAC

79% worth reading · novelty 1.9/3 · new method · cs.MA

09. Safety of Latent Communication in Multi-Agent Systems

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

10. MatLoom: Layered Text-to-Material Generation in a Compact Program Space

77% worth reading · novelty 1.9/3 · new method · cs.AI

11. ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents

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

12. EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

81% worth reading · novelty 1.6/3 · new method · cs.CL

13. Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets

78% worth reading · novelty 1.8/3 · new method · cs.MA

14. RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent

81% worth reading · novelty 1.6/3 · new method · cs.MA

15. DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

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

16. cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents

80% worth reading · novelty 1.5/3 · benchmark/eval · cs.AI

17. Consensus and Factual Dynamics in Large Populations of Interacting Language Models

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

18. How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

79% worth reading · novelty 1.4/3 · survey/position · cs.AI

19. SQD-Agent: LLM-driven agentic framework for Quantum Chemistry workflows

75% worth reading · novelty 1.5/3 · applied system · cs.MA

20. MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

75% worth reading · novelty 1.4/3 · new method · cs.CL