…Planned Active Retrieval and Reasoning for Multi-Hop Question Answering (2026) Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning (2026) Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents…
…researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, AutoTTS, that changes what researchers design: from individual…
…https://researchpod.app/episode/ba0b395b-4c69-4157-924e-99a339c1873b Generated automatically by ResearchPod — happy to take feedback from the authors. · Woah! That's not bad, thanks :) Get this paper in your agent…
…To optimize this hierarchical reasoning process , we introduce Hierarchical Relative Policy Optimization (HRPO), which decomposes policy optimization into streaming reasoning and deep reasoning phases, providing more fine-grained advantage assignment instead of…
…Spatial Tool-Use Elicits Reasoning for Spatial Intelligence Published on Jun 18 Submitted by leoli on Jun 19 Ropedia Authors: , , Shulin Tian , , Yuhao Dong , , , , , , , , Abstract S-Agent is a spatial reasoning framework…
…We propose a hybrid approach, namely In-Writing, that combines free-form reasoning and structured generation in a single call. The model first performs unconstrained reasoning and only applies structured decoding after…
…Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning (2026) COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation (2026) SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas…
…https://researchpod.app/episode/d109d582-a554-42dd-9c80-c1941b585f65 Generated automatically by ResearchPod — happy to take feedback from the authors. · Thanks a lot for creating this audio walkthrough! We really appreciate the…
…We revisit it by pairing BM25 with frontier LLMs that have better reasoning and tool-use abilities. To support researchers asking the same question, we introduce Pi-Serini , a search agent equipped…
…agents that explicitly models trial-and-error during long-horizon web research. In practice, deep search is not only a reasoning problem — it is also a search-control problem. Agents often face…