# Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams

arXiv: https://arxiv.org/abs/2605.25310 · HTML: https://mlsanity.com/paper/2605.25310/

## Key facts

- Cited by 1 papers in the map (data through 7 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Conditional probing: measuring usable information beyond a baseline](https://mlsanity.com/paper/2109.09234/) (2021)
- [ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario](https://mlsanity.com/paper/2501.10132/) (2025)
- [Monitoring Latent World States in Language Models with Propositional Probes](https://mlsanity.com/paper/2406.19501/) (2024)
- [Language Models Encode Numbers Using Digit Representations in Base 10](https://mlsanity.com/paper/2410.11781/) (2024)
- [Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers](https://mlsanity.com/paper/2501.17727/) (2025)
- [Probing Pretrained Models of Source Code](https://mlsanity.com/paper/2202.08975/) (2022)
- [Interpretability Illusions in the Generalization of Simplified Models](https://mlsanity.com/paper/2312.03656/) (2023)
- [Internal Representations as Indicators of Hallucinations in Agent Tool Selection](https://mlsanity.com/paper/2601.05214/) (2026)
- [LLM Agents Already Know When to Call Tools -- Even Without Reasoning](https://mlsanity.com/paper/2605.09252/) (2026)
- [Analysing the Residual Stream of Language Models Under Knowledge Conflicts](https://mlsanity.com/paper/2410.16090/) (2024)
- [Revisiting the Othello World Model Hypothesis](https://mlsanity.com/paper/2503.04421/) (2025)
- [The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces](https://mlsanity.com/paper/2410.13194/) (2024)
- [Tool Calling is Linearly Readable and Steerable in Language Models](https://mlsanity.com/paper/2605.07990/) (2026)
- [Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling](https://mlsanity.com/paper/2604.13386/) (2026)
- [Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents](https://mlsanity.com/paper/2603.12564/) (2026)
- [Do LLMs Build Spatial World Models? Evidence from Grid-World Maze Tasks](https://mlsanity.com/paper/2604.10690/) (2026)
- [Polar probe linearly decodes semantic structures from LLMs](https://mlsanity.com/paper/2605.14125/) (2026)

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

- [GRADE: Graph Representation of LLM Agent Dependency and Execution](https://mlsanity.com/paper/2606.22741/) (2026)

## Abstract (arXiv)

Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural probes have targeted static code or chain-of-thought text, not an agent's run-time call graph. A low-capacity edge probe on the residual stream of Qwen3-32B decodes the tool-call dependency graph well above both a Hewitt--Liang random-label control and a positional baseline. A counterfactual contrast between value corruption and structural perturbation indicates the signal tracks abstract topology rather than identifier values, and replicates under an independent, non-substring oracle. The non-positional component replicates on three further interactive multi-hop benchmarks and attenuates as call order alone becomes a sufficient proxy for dependency, vanishing in single-shot planning. Per-layer activation patching shifts the probe at a later, non-patched boundary, evidence that the representation propagates rather than passively reads out, though the realised tool call does not move. To our knowledge this is the first structural probe of an LLM agent's runtime tool-call dependency graph. Our claims concern representation, not behavioural control, and span two model families and one primary domain.