…Online Adaptation for Self-Improving Foundation Agents Published on May 11 Submitted by Seth Karten on May 13 Princeton University Authors: Seth Karten , , , , , , , Abstract A self-improving AI system for embodied agents…
…errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structural self-improvement . Existing surveys cover individual agent capabilities, multi- agent collaboration , or…
Papers arxiv:2605.10848 Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient? …
…AI-generated summary Distributed blackbox consensus optimization is a fundamental problem in multi-agent systems, where agents must improve a global objective using only local objective queries and limited neighbor communication. Existing…
… These simulations produce rich experiential learning signals, whose effectiveness is validated by significant improvements in agent performance on both in-domain and out-of-domain productivity evaluations. …
… However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. …
Papers arxiv:2605.08083 LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Published on May 8 Submitted by Chengsong Huang on May 11 3 Paper of the day Google Authors: Tong Zheng , , , , , , Runpeng Dai , , , Tianyi Xiong , , , Abstract AutoTTS automates test-time scaling strategy discove… …
Papers arxiv:2605.06924 A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency Published on May 7 Submitted by Do Xuan Long on May 11 Google Authors: , , , , Abstract A$^2$RD, an Agentic Auto-Regressive Diffusion architecture, addresses long video synthesis challenges through a closed-l… …
…agent performance feedback guides SimCoder to generate adaptive curricula near the learner's capability frontier, so that environments become increasingly challenging as the embodied agent improves. Three case studies on embodied navigation…
… AI-generated summary Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. …