Responsible Agentic Reasoning and AI Agents: A Critical Survey
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Information fusion for trustworthy AI is entering a pivotal stage, where Large Language Model (LLM)-based agents excel at integrating multi-source knowledge into coherent reasoning chains. However, these agents remain opaque and difficult to audit in the absence of embedded, in-loop safety mechanisms. Existing surveys treat reasoning, agentic behavior, and safety in isolation, leaving a gap in how to integrate them into practical, trustworthy agents. To address this, we present a survey at the intersection of these domains and introduce Responsible Reasoning AI Agents (R2A2), a class of agentic LLM systems that generate explicit reasoning traces while enforcing fairness, privacy, transparency, accountability, and auditability throughout the decision loop. We synthesize recent advances in chain-of-thought prompting, ReAct, tree/graph-of-thought structures, tool use, memory, retrieval, and agentic browsing, and integrate these with responsible AI principles into a unified evaluation framework. Furthermore, we propose an evaluation methodology for agentic reasoning with embedded safety mechanisms and outline a five-stage reproducible protocol: Curate, Unify, Probe, Benchmark, Analyze, to operationalize responsibility metrics. Overall, this taxonomy, metric suite, and framework advance the development of safe, transparent, and governable LLM-based agents. The project repository is available on GitHub § https://github.com/shainarazavi/Responsible-reasoning-agents.
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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it