# An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures

arXiv: https://arxiv.org/abs/2608.03735 · HTML: https://mlsanity.com/paper/2608.03735/

## Key facts

- Cited by 1 papers in the map (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 14 of its 90 references that are in the map.
- First posted on arXiv 4 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, 14 of 14)

- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation](https://mlsanity.com/paper/2505.23885/) (2025)
- [SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types](https://mlsanity.com/paper/2412.11757/) (2024)
- [X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System](https://mlsanity.com/paper/2505.15372/) (2025)
- [Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models](https://mlsanity.com/paper/2601.05366/) (2026)
- [Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective](https://mlsanity.com/paper/2603.14248/) (2026)
- [MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering](https://mlsanity.com/paper/2502.17253/) (2025)
- [GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation](https://mlsanity.com/paper/2604.24929/) (2026)

## Built on by (most cited first, 1 of 1)

- [BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla](https://mlsanity.com/paper/2610.19704/) (2026)

## Abstract (arXiv)

Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are converted into executable plans. We study the planner in a multi-agent system as the request-to-action interface and derive an actionable taxonomy of planning-grounding failures from failed real-world task executions. LLM-based analysis shows that these failures constitute an increasing share of unsuccessful executions as language-resource availability declines, with the strongest effects in low-resource languages. To test whether the taxonomy supports mitigation, we introduce TART, Taxonomy-Guided Actionable Representation, that makes the taxonomy's key aspects explicit to the planner and downstream sub-agents. Across multiple languages, three LLM backbones, two datasets, and two agentic configurations, TART consistently improves performance. On multilingual GAIA, it raises a state-of-the-art system's accuracy by 5.6 percentage points averaged across eleven languages spanning low- to high-resource settings.