arXiv Computation and Language
TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Oct 1
You're Hired: Strategic Model Selection for LLM Collaboration
arXiv:2609.38816v1 Announce Type: new Abstract: While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems r...
arXiv AI
Aug 26
Efficient LLM Collaboration via Planning
arXiv:2506.11578v5 Announce Type: replace Abstract: Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large models achi...
Hugging Face Trending Papers
Sep 30
You're Hired: Strategic Model Selection for LLM Collaboration
While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems remain bottlenecked on pre-defined and hand-crafte...
arXiv AI
Jul 8
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
arXiv:2607. 05775v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons.
arXiv Computation and Language
Sep 23
GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning
arXiv:2605.25200v3 Announce Type: replace Abstract: Travel planning in the real world is overwhelmingly a \textit{group} activity, yet existing LLM travel-planning benchmarks reduce it to a single us...
arXiv Computation and Language
Sep 23
CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems
CONCAT is a training‑free framework that improves the efficiency of large language model (LLM) based multi‑agent systems by clustering agents according to their initial answers and selecting cluster leaders based on confidence. It uses a Theory‑of‑Mind‑inspired heuristic to predict collaboration benefits between leaders, then prunes communications to form an ad‑hoc network that reduces latency. Experiments on three LLMs and benchmarks show up to 2.02× higher accuracy/latency ratio than LLM‑Debate and a 50.1% latency reduction on Qwen2.5‑14B‑Instruct without task‑specific training.