# ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2608.08605 · HTML: https://mlsanity.com/paper/2608.08605/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [SmartPlay: A Benchmark for LLMs as Intelligent Agents](https://mlsanity.com/paper/2310.01557/) (2023)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [Demystifying Chains, Trees, and Graphs of Thoughts](https://mlsanity.com/paper/2401.14295/) (2024)
- [MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration](https://mlsanity.com/paper/2311.08562/) (2023)
- [MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models](https://mlsanity.com/paper/2402.01620/) (2024)
- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks](https://mlsanity.com/paper/2503.02390/) (2025)
- [Adaptive Graph Pruning for Multi-Agent Communication](https://mlsanity.com/paper/2506.02951/) (2025)
- [Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents](https://mlsanity.com/paper/2601.20144/) (2026)
- [FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data](https://mlsanity.com/paper/2509.02473/) (2025)
- [CORE: Full-Path Evaluation of LLM Agents Beyond Final State](https://mlsanity.com/paper/2509.20998/) (2025)
- [Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling](https://mlsanity.com/paper/2604.08178/) (2026)
- [GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems](https://mlsanity.com/paper/2507.13190/) (2025)

## Abstract (arXiv)

Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for evaluation across methods. Outcome-only benchmarks discard collaborations, whereas LLM-as-Judge evaluation requires additional, model-dependent inference and can vary with the LLM and rubric. We introduce a generalizable evaluation framework that maps native MAS traces into a shared space of unified collaboration graphs, enabling different methods to be evaluated under the same representation, reference set, and metric panel. Candidate graphs are compared with a query-specific reference forest. Each forest is a benchmark-provided collection of verified-success graphs: it records diverse ways in which representative MAS methods can complete the task, rather than prescribing a unique optimal process. Instantiating the framework as ForestBench, we filter 844 collaboration-necessary queries from seven public datasets, precompute ten successful target-conditioned reference graphs per query, and evaluate six representative MAS frameworks. Controlled backbone, reference-construction, and perturbation studies test the stability and scope of evaluation. Once the benchmark forests are built, ForestBench scores a trace in milliseconds without further LLM inference, providing a reusable structural basis for comparing diverse MAS collaboration traces.