01.Concordat: Typed Sessions for LLM Agents

88% worth reading · novelty 1.9/3 ·applied system ·cs.MA

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

87% 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.Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents

76% worth reading · novelty 1.9/3 ·benchmark/eval ·cs.LG

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

79% worth reading · novelty 1.6/3 ·new method ·cs.MA

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

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

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

81% worth reading · novelty 1.3/3 ·new method ·cs.CL

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

78% worth reading · novelty 1.5/3 ·new method ·cs.CL

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

72% worth reading · novelty 1.8/3 ·benchmark/eval ·cs.AI

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

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

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

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

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

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

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

74% worth reading · novelty 1.5/3 ·new method ·cs.CL

14.Metacognitive Decoding: Efficient Inference for Diffusion Language Agents

69% worth reading · novelty 1.5/3 ·new method ·cs.CL

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

68% worth reading · novelty 1.4/3 ·new method ·cs.CL

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

70% worth reading · novelty 1.2/3 ·applied system ·cs.CL

17.Test-Time Communication in Trading Agent Swarms

64% worth reading · novelty 1.6/3 ·benchmark/eval ·cs.CL

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

63% worth reading · novelty 1.6/3 ·new method ·cs.MA

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

56% worth reading · novelty 1.9/3 ·new method ·cs.AI

20.Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families

52% worth reading · novelty 2.0/3 ·benchmark/eval ·cs.CL