arXiv AI
Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Aug 25
Most of the LLM routing gap is task type
The paper investigates why large‑language‑model (LLM) routers—systems that select the best model for each query—often fail to outperform a single best model. By evaluating 14 models on 294 questions across seven task types and three languages, the authors find that a simple static mapping of task type to model improves 21 of the 29 questions that routing could potentially solve, and that learned routers do not significantly exceed this performance. The study highlights that most routing gains stem from task‑type specialization rather than complex learned decision rules.
arXiv Computation and Language
Aug 26
Most of the LLM Routing Gap Is Task Type
arXiv:2608.23023v2 Announce Type: new Abstract: An LLM router picks which model should answer each query. The appeal is that models fail on different questions. Whatever single model is best overall...
arXiv AI
Sep 30
HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment
arXiv:2609.38006v1 Announce Type: new Abstract: Running a language model locally offers advantages in privacy, latency, and cost, but local hardware fits only small models, which are less capable tha...
arXiv AI
Oct 5
Dynamic LLM Routers are Often Misguided
Dynamic LLM routers aim to reduce inference costs by directing each query to the cheapest capable model. In a study of six commercial routers across 14 settings and eight task categories, none surpassed a simple random router that selects between two well-chosen models at the same cost, with some underperforming by over 10 percentage points. The authors identify four common patterns—difficulty blindness, length reversal, semantic matching, and roster suboptimality—that explain this gap and propose a new evaluation method and a simple two-model router that mitigates these patterns, though its advantage over random routing remains modest.
arXiv Computer Vision
Oct 27
Multi-Agent Relay Thinking
arXiv:2610.35219v1 Announce Type: new Abstract: Existing multi-agent collaboration (MAC) methods have primarily explored a group thinking collaboration topology, where agents independently generate s...
arXiv AI
Oct 15
DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an agent must f...