← cd ..

$ cat ./papers/2026-10-29.json

// 2026-10-29 · generated 29 Oct 2026

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

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

← 2026-10-28latest ↑2026-10-30 →

01.Concordat: Typed Sessions for LLM Agents

88% worth reading · novelty 1.9/3 ·new method ·cs.MA

02.Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis

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

03.EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

80% worth reading · novelty 1.7/3 ·new method ·cs.CL

04.Remembering Is Not Enough: Refining Memories and Learning When to Use Them in Multi-Agent Systems

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

05.Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents

74% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.LG

06.Can LLMs Uncover Hidden Physical Laws through Free Exploration?

73% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.AI

07.Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions

74% worth reading · novelty 1.8/3 ·benchmark/eval ·cs.AI

08.GEPA-Curator: Curated Learning for Self Improving Agents

80% worth reading · novelty 1.3/3 ·new method ·cs.CL

09.Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

75% worth reading · novelty 1.6/3 ·new method ·cs.CL

10.ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

77% worth reading · novelty 1.5/3 ·new method ·cs.CL

11.GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement

74% worth reading · novelty 1.6/3 ·new method ·cs.MA

12.Ontology-guided multi-agent reasoning for explainable differential diagnosis

81% worth reading · novelty 1.1/3 ·new method ·cs.MA

13.A Serious-Game Testbed for Self-Governing Human-Machine Institutions

68% worth reading · novelty 2.0/3 ·applied system ·cs.MA

14.Metacognitive Decoding: Efficient Inference for Diffusion Language Agents

70% worth reading · novelty 1.5/3 ·new method ·cs.CL

15.Follow the Gradient: Tracing Safety Degradation Back to Training Data

69% worth reading · novelty 1.4/3 ·new method ·cs.CL

16.Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model

65% worth reading · novelty 1.6/3 ·new method ·cs.MA

17.Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE

68% worth reading · novelty 1.3/3 ·applied system ·cs.CL

18.ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

57% worth reading · novelty 1.9/3 ·new method ·cs.AI

19.Test-Time Communication in Trading Agent Swarms

60% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.CL

20.VideoLVR: Latent Visual Reasoning over Grounded Video Evidence

54% worth reading · novelty 1.8/3 ·new method ·cs.AI