MétaCan
Menu
Back to cohort
Record W7125908856 · doi:10.1109/ase63991.2025.00067

Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents

2025· article· W7125908856 on OpenAlexaff
Benjamin Rombaut, Sogol Masoumzadeh, Kirill Vasilevski, Dayi Lin, Ahmed E. Hassan

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsQueen's UniversityHuawei Technologies (Canada)
Fundersnot available
KeywordsObservabilityDebuggingTransparency (behavior)SoftwareBenchmark (surveying)Semantic reasonerAutonomous agentCognitionModel-based reasoningClass (philosophy)

Abstract

fetched live from OpenAlex

Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform complex, open-ended tasks in domains such as software engineering, customer service, and data analysis. However, their high autonomy and opaque reasoning processes pose significant challenges for traditional software observability methods. To address this, we introduce the concept of cognitive observability—the ability to recover and inspect the implicit reasoning behind agent decisions. We present Watson, a general-purpose framework for observing the reasoning processes of fast-thinking LLM agents without altering their behavior. Watson retroactively infers reasoning traces using prompt attribution techniques. We evaluate Watson in both manual debugging and automated correction scenarios across the MMLU benchmark and the AutoCodeRover and OpenHands agents on the SWE-bench-lite dataset. In both static and dynamic settings, Watson surfaces actionable reasoning insights and supports targeted interventions, demonstrating its practical utility for improving transparency and reliability in Agentware systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.009
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.911
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.009
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.002
Science and technology studies0.0010.001
Scholarly communication0.0000.001
Open science0.0030.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.079
GPT teacher head0.372
Teacher spread0.292 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicExplainable Artificial Intelligence (XAI)French-language works237,207