The paper introduces SSR (Structural Signal Retriever), a deterministic, training‑free method for selecting relevant Agent Cards in large multi‑agent systems without exposing the full registry to an LLM orchestrator. SSR extracts structural lexical signals from Agent Card fields, weights them with inverse document frequency, and uses an Inverted Signal Index to score candidates efficiently. Experiments on synthetic benchmarks, MS MARCO, and end‑to‑end orchestration show that SSR cuts LLM input by 98.8 % and latency by 70.9 % at 1,000 agents, while preserving retrieval effectiveness and preventing operational failures seen with full‑catalog approaches.
arXiv:2607. 24791v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for applying large language models (LLMs) to enterprise document corpora, yet naive implementations encounter hard limits as corpus scale and query complexity grow.
arXiv:2608. 09934v1 Announce Type: cross Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors.
The study examines how three context‑engineering techniques—semantic layers, orchestration, and compaction—affect data agents that answer questions over heterogeneous data. Using seven large language models on 1,514 long‑horizon tasks, the authors identify three agent behavior groups (investigators, premature answerers, early stoppers) and show that each technique benefits only the group it aligns with, while sometimes harming others. Combining the techniques yields smaller net gains than the sum of individual effects, leading to guidance on selecting techniques based on agent behavior, task demands, and accuracy‑cost trade‑offs.
The paper introduces Enrich‑Retrieve‑Rank, a scalable method for discovering capabilities in large agent ecosystems. It replaces in‑context routing with an offline enrichment step that converts sparse metadata into searchable profiles, followed by an online retrieve‑then‑rank pipeline that returns a ranked shortlist without invoking candidates. Experiments show that as the number of capabilities grows from 10 to 7,278, the new approach maintains higher top‑1 accuracy and reduces cost by 70× compared to full‑context baselines.
arXiv:2610.20959v2 Announce Type: replace-cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this,...
Harbor Adapters is a unified evaluation infrastructure that ports over 80 agentic benchmarks, enabling arbitrary agents to be tested across complex environments. The authors performed a large‑scale evaluation of 8 models on 54 benchmarks, using Terminus‑2 and three native harnesses, revealing detailed agent capabilities and failure modes. They also created Harbor‑Index, a curated set of 82 challenging tasks from 29 benchmarks, designed to be affordable yet comprehensive, with the best model achieving a 28.0% pass rate.
arXiv:2605. 21850v2 Announce Type: replace-cross Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs.
arXiv:2606. 28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.
CB-Orchestrator is an adaptive framework for optimizing large language model (LLM) agent workflows. It separates workflow generation—via evolutionary search—from workflow selection, which is treated as a contextual bandit problem to enable sample‑efficient learning. The approach reduces training‑phase API token usage by up to 40.55% and overall token overhead by at least 29.73%, while outperforming baselines on five benchmarks, including the MATH dataset.
SpecMind is a Multi-Agent Retrieval-Augmented Generation system designed to support spectrum intelligence by reasoning over heterogeneous data sources such as policy proceedings, legal regulations, and license databases. The system coordinates specialized sub-agents that retrieve and synthesize knowledge, enabling autonomous agents to handle diverse query types. SpecBench, a Q&A dataset based on real-world license records and policy proceedings, was created to evaluate RAG systems in the spectrum domain, and experimental results show SpecMind outperforms traditional RAG systems with over an 80% win rate against strong baselines.
arXiv:2606. 11199v1 Announce Type: cross Abstract: We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track.
The paper introduces POrchestra, a proactive agentic orchestration framework that lets sub‑agents request harness adjustments during execution, enhancing adaptability to dynamic environments. It also proposes On‑Policy Orchestration Distillation (OPOD), which uses hindsight feedback from sub‑agents’ requests to provide targeted improvement signals for training the orchestration policy. Experiments on three long‑horizon benchmarks show that POrchestra boosts task success by about 9.1% over the best baseline, and with OPOD the improvement rises to 10.0%, while also improving cost‑performance trade‑offs.