PaperlayerView exact revision on arXiv

Source-linked AI summary

Small Language Model enabled Autonomous agent for Language-Conditioned Cognitive Radar

Minhaj Uddin Ahmad, Zakia Zaman, Shunqiao Sun, Mizanur Rahman

arXiv:2608.11596v1eess.SPcs.AIeess.SY

TL;DR

Radar processing pipelines often rely on fixed rules that generalize poorly to high-level task descriptions and dynamic environments. This paper develops an SLM-driven, physics-grounded agent that selects and executes array-processing tools, demonstrating reliable cognitive control when supported by radar-specific prompting and tool execution.

  • Problem

    Fixed-rule radar-processing pipelines generalize poorly to high-level task descriptions and dynamic environments, motivating more adaptable strategy selection.

    Source: §1 · p. 1

  • Method

    The paper develops an SLM-driven agent that maps natural-language commands to validated array signal-processing actions through radar-specific prompting and physics-grounded executable tools.

    Source: §1 · pp. 1–2, §2.1 · p. 2

  • Results

    Across six task categories and 180 trials, ablations show that radar-specific prompting and tool execution support reliable algorithm selection and numerical reporting.

    Source: §3.1 · p. 4

  • Takeaways & Limitations

    A small locally hosted language model can serve as a cognitive controller for radar signal-processing tools when guided by physical priors and executable computation.

    Source: §4 · p. 6

    Evaluation is limited to synthetic ULA data and a fixed tool suite, without demonstrating robustness on hardware radar data, other array geometries, or complex propagation environments.

    Source: §4 · p. 6

Abstract

from arXiv · show

Modern radar systems require adapting their processing strategies in response to changing interference, clutter, and data availability. This paper introduces a framework for a small language model (SLM)-driven autonomous agent designed for language-conditioned cognitive radar, functioning as an intelligent controller for a suite of array signal processing tools. Given a natural-language command, the agent extracts radar-operation-related cues, selects an appropriate sequence of signal-processing methods, configures parameters, and invokes executable tools for numerical computation. Experiments with a synthetic uniform linear array (ULA) radar demonstrate that, given a natural-language command, the agent performs meaningful algorithm selection across diverse scenarios for sidelobe control, jammer suppression, multiple-null beamforming, coherent-source handling, and low-snapshot direction-of-arrival (DOA) estimation. Ablation results show that radar-specific prompting and physics-grounded tool execution are both required for reliable decisions and hallucination-free numerical results.

1. INTRODUCTION

The paper frames language-conditioned cognitive radar as an SLM-driven autonomous agent that maps natural-language commands to array signal-processing actions. It combines a physics-grounded executable toolchain with radar-specific mechanisms to support reliable, constraint-aware numerical reporting.

Motivation

  • Array-radar performance depends on selecting signal-processing strategies suited to operating conditions, but conventional designs generalize poorly to high-level task descriptions and dynamic environments.Examples include sidelobe-controlled beamforming for cluttered scenes and adaptive beamforming when needed.Source: §1 · p. 1

Framework

  • The proposed framework uses an SLM-driven autonomous agent as an intelligent user-facing controller for array signal-processing tools in language-conditioned cognitive radar.The agent is motivated by cognitive radar’s closed-loop adaptation paradigm and advances in language-model tool augmentation.Source: §1 · p. 1

Contributions

  • The paper formulates language-conditioned cognitive radar as a tool-augmented SLM-agent problem that maps natural-language commands to array signal-processing actions.This formulation is listed as the first main contribution.Source: §1 · pp. 1–2
  • A modular physics-grounded radar toolchain derives numerical claims from executable signal-processing routines rather than model-generated arithmetic.The toolchain is intended to support numerical reliability and reduce hallucinated reporting.Source: §1 · p. 2
  • Radar-specific prompting, parameter validation, state management, and transcript logging enforce physical constraints and reduce hallucinated numerical reporting.These mechanisms are identified as part of the paper’s main contributions.Source: §1 · p. 2

2. METHOD

The method uses a modular SLM-based autonomous agent to implement a language-conditioned cognitive-radar processing loop. It parses natural-language input into radar-relevant cues and selects processing actions from a predefined array-signal-processing library.

2. METHOD

  • The SLM-based autonomous agent is designed with a modular architecture for cognitive radar.Figure 1 presents the language-conditioned cognitive-radar processing loop.Source: §2 · p. 2
  • The loop begins by parsing input into structured cues including target and interference directions, clutter, snapshot support, and resolution constraints.These cues represent the radar-operation information used to guide subsequent processing decisions.Source: §2 · p. 2
  • Using the extracted cues, the SLM agent selects a processing action from a predefined library of array signal-processing methods.The architecture therefore connects language-conditioned cue extraction with radar algorithm selection.Source: §2 · p. 2

2.1. Physics Tools

The Physics Tools module provides a physics-informed Python foundation for language-conditioned radar processing, combining array simulation, beamforming, and DOA estimation. Its algorithms support scenario-dependent weighting, interference suppression, and source-direction estimation while reducing hallucinations in numerical outputs.

Module organization

  • The standalone NumPy/SciPy package groups tools into an array simulator, beamforming methods, and DOA estimation methods.These functions provide the physics-informed foundation for the SLM’s numerical outputs and help reduce hallucinations.Source: §2.1 · p. 2

Array simulation

  • The array simulator generates narrowband ULA snapshots from a standard signal model and serves as a surrogate for actual radar hardware.Windowing options include uniform, Dolph-Chebyshev, and Taylor weights for scenario- and requirement-dependent sidelobe control.Source: §2.1 · p. 2

Beamforming

  • Beamforming tools include DAS, MVDR, MPDR, and LCMV, with MVDR and MPDR minimizing interference-plus-noise power while preserving unit target-direction gain.DAS applies uniform or tapered steering-vector weights; MVDR and MPDR differ primarily in their covariance-matrix usage.Source: §2.1 · p. 2

DOA estimation

  • DOA tools include MUSIC, ESPRIT, and OMP, using subspace orthogonality or rotational invariance to estimate source directions.MUSIC identifies directions through steering-vector orthogonality with the noise subspace, while ESPRIT uses two overlapping subarrays without grid search.Source: §2.1 · p. 2

2.2. SLM based Autonomous Agent

The autonomous agent uses a locally deployed, 4-bit quantized Qwen3.5 model and a ReAct-style tool-calling loop to control radar signal-processing workflows. Radar-specific prompting supplies algorithm-selection knowledge and physical constraints, while tool execution and persistent run context support reliable numerical processing.

Model deployment

  • Qwen3.5 is deployed as a locally served, 4-bit quantized 9B-parameter SLM suitable for embedded radar platforms.The local Ollama deployment also supports offline operation and future model upgrades without changing the radar signal-processing pipeline.Source: §2.2 · pp. 2–3

Agent loop

  • The agent follows a ReAct-style observe-reason-act loop that streams full conversation history and invokes tools until producing a turn without tool calls.The loop accepts reasoning, provider-schema tool calls, or both, then treats a tool-free turn as the final human-readable answer.Source: §2.2.1 · p. 3

Radar-specific prompting

  • The system prompt supplies radar expertise, algorithm operating conditions, selection rules, and physical constraints because the general-purpose SLM lacks radar-specific fine-tuning.Examples include snapshot requirements for MUSIC, jammer modeling, MVDR versus MPDR selection, Rayleigh resolution, source capacity, and MUSIC rank conditions.Source: §2.2.2 · p. 3

Execution constraints

  • Every tool call must be preceded by explicit reasoning, and final numerical results must come only from tool outputs.The loop inserts a nudge message when the model produces an empty answer, reinforcing non-empty final responses.Source: §2.2.2 · p. 3

Tool integration

  • A persistent RunContext preserves numerical results across stateless tool calls, enabling sequential simulate-then-process-then-analyze workflows.Subsequent handlers can reuse and update values stored during the same invocation.Source: §2.2.3 · p. 3

3. EXPERIMENTAL EVALUATION

The evaluation tests both the agent’s decision-making reliability and the physics-grounded radar performance of its selected tools. Experiments use paraphrased natural-language tasks spanning six radar-processing categories, ablations, scenario-specific beamforming and DOA tests, and runtime measurements.

Evaluation objectives

  • The evaluation measures tool or tool-sequence selection, valid tool calls, physically valid parameters, and avoidance of hallucinated numerical results.It also examines whether selected tools achieve requested sidelobe levels, jammer suppression, and DOA-estimation performance.Source: §3 · p. 4, §3.1 · p. 4

Benchmark design

  • The benchmark covers six radar-processing categories using paraphrased commands, repeated trials, and expert-defined acceptable tool or tool-sequence labels.This design tests natural-language robustness rather than memorization and accounts for stochastic variation in SLM responses.Source: §3 · p. 4, Table 1 · p. 4

Ablation study

  • The ablation compares the full agent with agents lacking radar-specific prompting or tool execution and with a fixed keyword-matching controller.Without domain-specific prompting, the SLM may confuse similar methods such as MVDR and MPDR; without tools, it cannot reliably produce numerical radar values.Source: §3.1 · pp. 4–5

Sidelobe control

  • For a 30◦ scan direction and sidelobes below −30 dB, the agent selected delay-and-sum beamforming with a Dolph-Chebyshev taper.The taper is described as providing the narrowest mainlobe for a prescribed equiripple sidelobe level.Source: §3.2 · p. 5, Table 3 · p. 5

Adaptive beamforming and DOA estimation

  • The experiments evaluate adaptive beamforming under high-power jamming and DOA estimation under limited snapshots, closely spaced sources, and coherent-source conditions.The DOA discussion distinguishes MUSIC, ESPRIT, and OMP according to covariance reliability, snapshot stability, and sparse-recovery suitability.Source: §3.3 · p. 5, §3.4 · p. 5, Table 4 · p. 6

Runtime

  • Runtime measurements include SLM generation, tool-call parsing, physics execution, and final response generation, with local model generation identified as the main bottleneck.The experiments use an Intel i9-14900F CPU, 64GB of RAM, a quantized 9B-parameter SLM, and lightweight NumPy/SciPy processing.Source: §3.5 · p. 5

N L SNR True DOAs Selected tool Estimated DOAs / RMSE · 4. CONCLUSION AND FUTURE DIRECTION

The paper presents an SLM agent that reliably controls radar array signal-processing tools when guided by a carefully engineered system prompt. Its evaluation remains limited to synthetic ULA data and a fixed radar-tool suite.

4. CONCLUSION AND FUTURE DIRECTION

  • The system uses an SLM agent for radar array signal processing.The agent is designed as a controller for radar signal-processing operations.Source: §4 · p. 6
  • Qwen 3.5:9b serves as a locally hosted cognitive controller for a suite of signal-processing tools.The paper characterizes the model as small and locally hosted.Source: §4 · p. 6
  • Reliable control depends on a carefully engineered system prompt.The prompt encodes algorithm-selection priors, physical sanity checks, and behavioral-discipline constraints.Source: §4 · p. 6
  • The system prompt encodes algorithm-selection priors for the agent.These priors are part of the prompt conditions associated with reliable control.Source: §4 · p. 6
  • The system prompt includes physical sanity checks and behavioral-discipline constraints.Both elements are identified as components of the engineered prompt.Source: §4 · p. 6
  • The current evaluation uses synthetic ULA data and a fixed radar-tool suite.The paper identifies these evaluation choices as remaining limitations.Source: §4 · p. 6

Related papers

Loading 2608.11596v1…