← cd ..

$ cat ./papers/2026-10-14.json

// 2026-10-14 · generated 14 Oct 2026

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

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

← 2026-10-13 latest ↑ 2026-10-15 →

01. The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement

82% worth reading · novelty 2.7/3 · new method · cs.CL

02. Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards

85% worth reading · novelty 2.1/3 · new method · cs.AI

03. Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

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

04. ChunkAct: Action Chunking for Agentic Robotics

86% worth reading · novelty 1.7/3 · new method · cs.AI

05. PlanPath: Exploration-Guided Orchestration for Patient-Level Pathology Reasoning

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

06. Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables

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

07. Hybrid Reasoning Agents

85% worth reading · novelty 1.8/3 · new method · cs.AI

08. MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

82% worth reading · novelty 1.9/3 · new method · cs.MA

09. ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning

83% worth reading · novelty 1.8/3 · new method · cs.MA

10. BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems

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

11. Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made

79% worth reading · novelty 2.0/3 · new method · cs.MA

12. Origin Attribution for Unsafe Behavior in Self-Evolving Multi-Agent Coding Systems

80% worth reading · novelty 1.9/3 · new method · cs.MA

13. Self-Evolving Agent Harness

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

14. SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection

83% worth reading · novelty 1.6/3 · new method · cs.CL

15. Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges

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

16. SEAR: Self-Evolving Agentic Robotics

83% worth reading · novelty 1.6/3 · benchmark/eval · cs.CL

17. Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes

76% worth reading · novelty 1.7/3 · new method · cs.MA

18. AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

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

19. DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning

70% worth reading · novelty 1.7/3 · new method · cs.AI

20. Choosing LLMs for Strategic Agent Interactions

63% worth reading · novelty 1.9/3 · benchmark/eval · cs.MA