cs.AINov 13, 2026

Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners

Authors: Stephen Obadinma, Xiaodan Zhu

Organizations: Department of Electrical and Computer Engineering, Ingenuity Labs Research Institute, Queen’s University

Abstract

As large language models (LLMs) are increasingly deployed as autonomous agents, their abilities in navigating automated planning tasks have become essential. However, despite their strengths, LLMs' planning ability is not robust, particularly when they are not allowed to exploit commonsense cues in the symbolic vocabulary (e.g., names of actions, predicates, and objects) used to define planning tasks. This makes LLMs unreliable compared to symbolic planners. With recent reasoning models showing improved planning performance on tasks with obfuscated symbolic vocabularies, we utilize an adversarial attack framework to reveal to what extent the crucial weaknesses of LLM agents at joint symbolic interpretation and planning remain and whether they can reason properly when presented with severe cases. As such, our main contribution is devising an LLM-based attack model, which we call Symbolic Swapper, to automatically generate obfuscated planning domains with non-standard symbolic vocabularies that systematically break strong reasoning models' ability to plan. In doing so, we reveal how much LLMs' planning abilities can be further degraded under more advanced obfuscation schemes, allowing us to ascertain their success when having to rely on their pure planning ability. We find that attacks can decrease the planning performance of base models and even robust planning frameworks by over 70%. We further analyze the factors behind how LLM planning abilities break down and find that successful obfuscation causes models to appear to significantly degrade in reasoning quality despite them showing some inherent ability to understand the domain, revealing a gap in the perception of a task domain and being able to plan under it.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 2, 2025

How Far Are LLMs from Symbolic Planners? An NLP-Based Perspective

AI planning provides agents the ability to act autonomously towards achieving a goal in a given environment. Recent advances in Large Language Models (LLMs) have introduced the prospect of using unstructured input for planning, making LLMs in planning an active area of research, especially for supporting autonomous agents. However, LLMs remain unreliable as long-horizon planners, since some of the plans they produce contain mistaken or hallucinated actions; executing such plans could lead to unexpected and harmful outcomes. Existing benchmarks for LLMs in planning primarily rely on binary evaluation metrics, providing limited insight into the quality of plans that do not achieve the goal, and how far those are from becoming valid. In this paper, we frame the evaluation of LLMs in planning as a natural language processing (NLP) task, as LLMs are themselves NLP models. We propose a pipeline comprising three NLP-based steps that assess plan quality from complementary perspectives, followed by a symbolic planning step to achieve a valid plan, to provide a finer-grained understanding of the quality of invalid plans. In our experiments, we find no clear evidence of logical derivation or state-tracking during LLM plan generation -- on average, for all non-empty plans, only 3.55 actions per plan are executable, despite symbolically-generated optimal plans having an average length of 9.47 actions, which suggests that LLMs are still far from the reliability of symbolic planners. Our suite of metrics is further used to investigate patterns in LLM plan generation over time, and can provide a useful metric for assessing the quality of individual invalid plans.
Oct 18, 2026

When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability

Large language models (LLMs) struggle with classical planning, but benchmarks rarely distinguish structural difficulty from the difficulty of interpreting symbolic vocabulary. We examine seven STRIPS domains with BFS-optimal plan lengths. For predicting structural difficulty without solving an instance, the zero-training delete-relaxation heuristic haddh_{\mathrm{add}} outperforms learned alternatives on held-out domains (mean Spearman ∣ρ∣=0.931|ρ|=0.931), including ridge regression (0.7070.707), object count (0.6570.657), and the episodic retrieval architecture ARC (0.4000.400). ARC also fails to outperform a linear model using the same features. To isolate semantic effects, we progressively rename predicates while preserving states, transitions, and optimal plans. Valid LLM planning success drops from 67.5%67.5\% to 40.0%40.0\% between 0%0\% and 100%100\% renaming, while refusals remain at 0%0\%. An LLM supplied with ARC's conditioning information predicts difficulty in context better than trained ARC (mean ∣ρ∣=0.826|ρ|=0.826). Hybrid routing between an LLM and a symbolic planner depends more on calibration to the target LLM's outcomes than on the structural score selected. Thus, established symbolic heuristics already estimate structural difficulty well; improving hybrid planning requires modeling LLM behavior sensitive to predicate semantics rather than developing more structural predictors.
Jun 12, 2026

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks evaluate whether LLM-generated plans execute successfully, they overlook a critical type of failure: latent failures. Unlike immediate failures that trigger instant feedback at execution time and enable timely correction, latent failures do not immediately halt plan execution but silently compromise goal achievement. In severe cases, they cause irreversible harm. To address this gap, we introduce SIMMER, a benchmark for evaluating latent failures in LLM planning through a human-curated symbolic world model grounded in the kitchen domain. SIMMER defines a world model comprising 77 actions, 262 unique objects, and approximately 46,800 possible interactions that are semantically realistic, derived from real-world cooking scripts. It then leverages a state machine executor that validates plans against the world model and detects immediate precondition violations, latent hazards, and irreversible failures. Experiments across six LLMs show that even frontier models achieve at most 17% error-free plans. Moreover, up to 56% of plans contain latent failures, the majority of which lead to irreversible consequences. We further demonstrate that explicit state reasoning via counterfactual foresight simulation can reduce latent failures by up to 72% and irreversible cases by up to 75%, suggesting a promising direction for more robust LLM planners.