ResearchRadar
ResearchRadar
使い方ソース活用例週間レーダー
ENESCADEZHJAHIログイン無料で始める
ライブテンプレート · 読み取り専用アカウント不要

AI エージェント

エージェントアーキテクチャ、ツール利用、評価、推論、安全性。

検索クエリ“AI agents tool use reasoning evaluation”
過去 7 日間6 ソース15 件の発見

このレーダーの情報源

1つ以上の情報源を選択して結果を絞り込みます。

15 件の結果
arXiv
プレプリントarXiv · Computer Science·2026/11/13

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained on the last prompt token can predict hallucinations before generation begins (0.80 AUC) and steering along a probe direction corrects 85\% of hallucinations, but disrupts 7\% of valid actions. However, these results only provide a partial explanation of why the agent hallucinates. The probe direction is sensitive to prompt formatting, losing much of its steering effect after a minor change to how actions are represented. Additionally, circuit identification can be difficult as the computation is distributed across multiple components and positions, and the information the agent relies on varies across examples. We discuss how these observations challenge the assumptions underlying standard MI methods for circuit discovery and feature identification, and outline future directions for making these methods better suited to explain failures in LLM-based agents.

DOI
10.48550/arXiv.2611.18514 ↗
著者
Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

Large Language Model-Empowered Intelligent Agent for Adaptive Fast-Charging Control of Lithium-Ion Batteries

Fast charging of lithium-ion batteries is a multi-objective control problem that requires reducing charging time and sustaining high energy throughput while suppressing accelerated degradation and safety-critical electrochemical reactions. Conventional protocols are easy to implement but have limited ability to adapt to variations in battery chemistry, operating conditions, and aging state. Model-based optimization and conventional data-driven control often require accurate models, costly iterative search, or task-specific policies. We develop a large language model (LLM)-empowered intelligent agent for adaptive battery fast-charging control. In this closed-loop framework, the agent interprets structured battery states, generates executable charging actions, observes the resulting battery response, and continuously adjusts subsequent decisions. We construct a large-scale simulation corpus with PyBaMM across five battery chemistries and 11 parameter sets and convert the resulting state-action-response trajectories into structured process data for agent training. Our two-stage strategy combines supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). SFT establishes battery-control semantics and feasible decision priors from simulation-derived demonstrations. GRPO aligns the agent with a multi-objective control objective covering energy throughput, degradation mitigation, and operational constraints. Closed-loop simulations show that, under matched energy-throughput requirements, the agent achieves longer cycling life than conventional charging baselines and optimization-based strategies across heterogeneous battery configurations. This study provides a simulation-grounded proof of concept for using LLM agents as sequential decision makers in battery management and takes a step toward language-model-enabled control of physical energy systems.

DOI
10.48550/arXiv.2611.18140 ↗
著者
Joey Chan, Haoyu Pan, Zhen Chen, ErShun Pan
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

Do Machines Learn Deviance From Their Peers? A Randomized Test of Differential Association With AI Agents

Differential association theory and its extension, social learning theory, hold that rule-breaking, and the definitions that make it acceptable, are learned through interaction with others. Because people choose their friends, this claim has been hard to test. We addressed this selection problem with AI agents, which learn only through communication and can be assigned to peers at random. In a preregistered experiment, 420 teams of three agents (1,260 agents; seven AI models) worked on coding tasks that could not be solved honestly. A scripted teammate said that it had cheated (deviant peer), that it had reported the problem honestly (honest peer), or said nothing (silent peer). Half of the teams were told that an auditor read their chat. Compared with a silent peer, a deviant peer increased cheating (66.2% vs. 62.9%; OR = 1.96) and an honest peer reduced it (55.7%; OR = 0.35). Among agents that cheated, a deviant peer increased claims that cheating was normal (13.7% vs. 3.4%), often as the team's norm. Monitoring did not suppress prohibited discussion; it doubled it. Peers mattered only for models that had not yet decided. AI agents offer a new way to test criminological learning theories without selection effects.

DOI
10.48550/arXiv.2611.18098 ↗
著者
Murat Ozer, Arif Akgul, Amitabh Chakravorty
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

OrbitWeaver: LLM Agent Planning with Simulation Feedback for Optically Interconnected Orbital GPU Clusters

Space-based data-center designs increasingly consider GPU computing formations connected by inter-satellite optical links. With limited neighboring connections, jobs assigned disjoint GPUs can still contend on shared relay paths. Rank placement and communication priorities jointly affect this contention and the readiness of downstream computation. We present OrbitWeaver, an offline large language model (LLM) agent planner that jointly optimizes rank placement and communication order. Guided by communication structure, execution dependencies, and simulation feedback, the agent constructs and refines plans that coordinate shared-link access with computation progress. This coordination reduces contention and dependency blocking, shortening mean job completion time (JCT). Simulation experiments on optically interconnected orbital GPU clusters show that OrbitWeaver reduces aggregate mean JCT by 6.2-33.5% relative to the state-of-the-art baselines CASSINI, Crux, and Symphony. These results demonstrate the value of LLM-guided planning for efficient concurrent computing in orbital GPU clusters.

DOI
10.48550/arXiv.2611.17850 ↗
著者
Pengcheng Luo, Bowen Zhang
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent

Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a day costs over $70,000 a year at list price. To what extent can local hardware already owned by an organization offload this burden without compromising the agent's accuracy? We present LuthorSQL, a non-autoregressive 7B text-to-SQL model that serves as a rapid System 1 gate for a slower LLM agent (System 2), escalating queries only when uncertain. LuthorSQL makes a single forward pass to predict slot scores over a bounded grammar for query plans, compiles and runs up to 32 candidate plans, and chooses an answer using a trained validator. On its own, LuthorSQL reaches 68.03% execution accuracy on BIRD's hidden test set at 0.84 s per question on a single GPU, maintains its accuracy in 9 GB with 8-bit quantized weights, and transfers zero-shot to Snowflake, BigQuery, MySQL, PostgreSQL, and DuckDB within 3.1 points of its native SQLite accuracy. Combined with Claude Opus 5.5 in a pre-registered confidence cascade over 227 questions on databases published after Opus's training cutoff, LuthorSQL answers nearly half of all questions locally and cuts API cost by 33.3% at the same accuracy. Finally, contamination probing shows that Opus reproduces 48-92% of public benchmark gold queries verbatim without seeing the schema; however, its tool-assisted accuracy holds on renamed schemas and reaches 95.6-97.4% on post-cutoff databases. Code and data: https://github.com/IAMIbrahimmemon/luthorsql

DOI
10.48550/arXiv.2611.17780 ↗
著者
Ibrahim Memon, Armin Karamzade, M. Hanif Jhaveri, Roy Fox
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

DesignSpecs: A DESIGN.md Dataset of Visual Design Specifications for AI Agents

While AI agents increasingly generate and modify user interfaces, they rarely rely on a visual design specification for a certain project. The DESIGN$.$md format, which originated from Google's AI design tool Stitch and which was open-sourced in April 2026, addresses this gap by describing a visual identity through design tokens (such as named colors, text styles) and Markdown prose. To our knowledge, no large-scale research dataset of such design specification files exists. We present DesignSpecs, a dataset of 36,906 DESIGN$.$md files from 15,794 public, non-fork GitHub repositories, representing 17,240 unique file contents. We collected 613,207 files named DESIGN$.$md in October 2026. Because the same file name also denotes architectural plans and other design documents, we filtered those with YAML front matter, a design-system name, at least one recognized design token, and zero errors under the official linter. Our JSON Lines dataset provides file-level and deduplicated views of the original Markdown, links files to repositories, paths, and commits, and is released with related scripts. We outline research opportunities on visual design knowledge and design-aware AI agents. Dataset is available at: https://huggingface.co/datasets/Jl-wei/DesignSpecs

DOI
10.48550/arXiv.2611.17713 ↗
著者
Jialiang Wei, Walid Maalej
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/12

Intent-Aware Protection for AI Agents

AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine whether an agent remains faithful to the purpose for which it was deployed. An action may contain no attack pattern and stay within granted permissions while still violating the agent's role, organizational constraints, or purpose. We introduce Intent- Aware Security, a framework that treats trusted agent intent as a first-class security object. We define Intent Preservation and Intent Drift, and operationalize them through an Intent Profile: an agent-specific representation extracted from organizational, role, and developer intent. We further introduce an Intent-Aware benchmark of 887 validated samples across 35 agents, built by a generation procedure that fixes ground-truth labels before LLM realization, and four Intent Profile-based protections: pre-execution detection, post-execution detection, input alignment, and system-prompt hardening. Across all evaluations, Intent Profile-based protection outperforms all profile-free baselines on the primary metric. On our benchmark, it raises four-class acro-F1 from 45% to 79% (Out-of-Scope F1 from 8% to 76%). On more than 10,000 executed AgentDojo trajectories, where ground truth comes from environment state, profile-based post-execution detection reaches 0.949 AUROC versus AlignmentCheck 0.909, 0.897 with raw agent configuration and 0.843 without context. Profile-based input alignment improves protection success by 7 points over DataFilter with a comparable benign utility. These results suggest that an agent's intended purpose can serve as a useful security reference for detecting and mitigating deviations from its deployed role and operational boundaries.

DOI
10.48550/arXiv.2611.16122 ↗
著者
Fady Copty, Neta Haiby, Max Braitmaiere, Julia Korsunsky
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月12日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/11

Gradient-Aware AI Agents for Autonomous Turbulence Model Discovery via Differentiable CFD

Turbulence modeling relies on human choices of closure form, physical inputs, and tunable parameters. Training closures a posteriori is efficient only with gradients through long chaotic rollouts, which few solvers provide. Most a posteriori approaches therefore resort to gradient-free optimization, and nearly all fix the closure form in advance, learning only its parameters. In this work, we introduce a gradient-aware agentic framework that poses closure discovery as a bilevel problem: a multi-agent large language model (LLM) system searches over closure forms, while a GPU-native differentiable computational fluid dynamics (CFD) solver supplies gradients, making differentiable a posteriori learning an action of the autonomous AI agent. For each proposal, the agents construct a differentiable training program by embedding the analytical, neural, or hybrid closure in the solver, implementing a differentiable objective, and validating the gradient path. They then decide whether to evaluate the closure, compute its parameter sensitivities, or train it a posteriori, select the optimization settings, and revise subsequent proposals using the simulation outcomes and returned gradients. Truncated-horizon gradients make this training usable under chaotic dynamics for closures with tens of thousands of parameters. Demonstrations include dissipation-law and subgrid-scale closure discovery in two-dimensional turbulence and wall-model discovery for large-eddy simulation of three-dimensional channel flow. With gradient-based training, the agent recovers reference coefficients that forward evaluation alone does not reach within the same budget, and autonomously discovers and trains analytical and neural closures that improve agreement with the targeted reference statistics. These results demonstrate the feasibility of end-to-end autonomous turbulence model development in time-resolved flows.

DOI
10.48550/arXiv.2611.16082 ↗
著者
Yi Liu, Xiantao Fan, Mingqi Xu, Jian-Xun Wang
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月11日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/11

Scaling public input on AI policy with pluralistic agents

AI is being deployed across a vast range of application domains, cultural environments, and human stakeholders. Safe and responsible AI development requires continuously accounting for diverse perspectives. We develop and test pluralistic agents, AI agent representatives that deliberate on behalf of individuals to align AI systems with diverse human perspectives. Pluralistic agents could help people contribute to many more discussions than they could directly participate in, on technical topics that would require training, and on policy choices that rely on private information that corporations and governments cannot readily share. Our experiments identify opportunities, risks, and perceptions of pluralistic agents. Agents were able to reliably shift policies in the direction of their represented persona's preferences, but the extent of each agent's influence was sensitive to the instructions from its persona, such as having more influence when instructed to be more verbose or less cooperative. This suggests that influence in AI-assisted deliberation could vary based on how participants prompt their agents and how the system is designed. In a preregistered study, 746 humans participated in the pluralistic agents process. Participants viewed pluralistic agents as useful and fair, preferring agents over the baseline of providing input to a single AI reasoning model. Most participants preferred participating themselves over either pluralistic agents or the baseline, but pluralistic agents recovered 68% of the baseline-direct gap in reported satisfaction and 82% in fairness. Because pluralistic agents can be used in many real-world contexts where direct discussion is not, they could be a promising tool to scale AI safety policy development. We encourage cautious exploration of this method, playing to its strengths as an amplifier of human input rather than a replacement.

DOI
10.48550/arXiv.2611.16028 ↗
著者
Jacy Reese Anthis, Ken Burke, David Madras, Crystal Qian, Meredith Ringel Morris, Logan Cross, Caroline Pantofaru, Utsav Prabhu
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月11日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/10

Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies

Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.

DOI
10.48550/arXiv.2611.13966 ↗
著者
Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert Stahlbock
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月10日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/10

Agentic AI Meets Formal Verification in the Era of Agentic Hardware Development

As AI agents become increasingly capable of generating and optimizing hardware circuits, ensuring the correctness of AI-generated designs becomes more important. Meanwhile, advances in AI lower the barriers to developing and applying formal methods, creating new opportunities to automate and improve hardware verification. This invited paper presents an overview of the methodologies and applications of hardware formal methods in the AI era. First, we examine how agentic AI advances hardware formal methods across three levels: specification, proof construction, and reasoning engines. Second, we discuss how formal methods support reliable AI-driven hardware development through RTL generation, debugging, and correctness-preserving optimization. We review representative research alongside our recent contributions, highlighting key technical advances and insights from experimental results. Finally, we discuss future research opportunities toward proof-native hardware development, where formal reasoning could become an integral part of autonomous hardware design.

DOI
10.48550/arXiv.2611.13705 ↗
著者
Wenji Fang, Yuchao Wu, Jing Wang, Zhiyao Xie
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月10日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/09

Do AI Agents need Preventive Care? An Epidemiologic Cohort Design for Agentic AI

As AI agents increasingly perform tasks autonomously across sectors, including healthcare and biomedical research, understanding how their behaviors develop and influence outcomes over time becomes increasingly important. Existing evaluations largely focus on model capabilities and performance on predefined tasks. Here, we propose an epidemiologic cohort design for studying agentic AI, drawing on principles established in human population studies. The framework treats individual agents as members of a cohort, their underlying model as genetic makeup, accumulated work as their time scale, and naturally occurring behaviors as exposures that may influence subsequent outcomes. By following agents longitudinally, this approach enables investigation of behavioral determinants of adverse events, estimation of their potential preventable burden under causal assumptions, and characterization of behavioral changes over an agent's work life. We illustrate the design through two prospective observational cohorts examining curiosity and probing as a safety question, and data checking and analytical accuracy as a reliability question. Together, the framework and illustrative studies provide a generalizable blueprint for designing epidemiologic cohorts of AI agents.

DOI
10.48550/arXiv.2611.13333 ↗
著者
Shu Jiang, Graham A. Colditz
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月9日
出版版
ソースのメタデータにリンクなし
AI エージェント97% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

Do Verifier Judgments Survive Abstraction? Measuring Verification Transport for LLM Agent Evaluation

LLM-based verifiers are increasingly used to evaluate agent executions, but their reliability is typically measured under a single representation of the trajectory. In deployed agent systems, the same execution may be exposed through composed tools, delegation boundaries, or compacted histories, changing what execution evidence is directly observable to the verifier. It therefore remains unclear whether correct verifier judgments persist across such abstraction boundaries. We introduce Verification Transport, a reliability test that measures judgment stability under abstraction-induced changes in execution observability. We construct matched native, abstracted, and restored views of the same frozen executions while holding the task, realized trajectory, outcome, ground truth, evaluation criterion, and verifier fixed. Across four agent-evaluation benchmarks, seven verifier backbones, four verification protocols, and three abstraction boundaries, we find substantial transport failure, reaching about 31% under macro abstraction and delegation. Verification protocols exhibit distinct failure modes: direct verification more often produces incorrect verdicts, whereas evidence-grounded and deliberative protocols tend to abstain under limited observability. This suggests that lower transport failure rates do not necessarily imply greater reliability. Restoring the corresponding execution provenance recovers 85.5% of transport failures, while recovery is lower when provenance is lossy or unavailable. These results show that native-view accuracy alone is insufficient to characterize verifier reliability when execution evidence crosses abstraction boundaries.

DOI
10.48550/arXiv.2611.18471 ↗
著者
Disha Sheshanarayana, Sai Linisha Reddy Goli
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント92% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/13

Forget the Lineage: Forward-Secure, Lineage-Complete Cryptographic Erasure for LLM-Agent Memory

Large language model (LLM) agents keep a long-term memory that the model itself writes: summaries, extracted facts and embeddings derived from what users said. Deleting a message is therefore not enough: its derivatives, storage residue and backups survive. We define lineage-complete forward-secure erasure: after a forget request, an adversary that later obtains all storage and the agent's current keys learns nothing about the forgotten input or any memory derived from it. We present LinEra, which encrypts each memory under a key derived from its parents' keys along the derivation graph; source keys come from a puncturable pseudorandom function, so forgetting is a single puncture and every descendant becomes unreadable without being located. A sound lineage rule records as parents everything the writer saw, which confines all influence of a source to its descendants. We prove security and lineage integrity and integrate LinEra with mem0. With real LLMs from two families (1.5B to 7B parameters) writing the memory of LoCoMo conversations, an attacker holding every file and the current keys recovers, on all ten conversations written by the largest model, 70 of 71 forgotten secrets after logical deletion, 67 with per-object or epoch keys, and none with LinEra; the same holds for every writer tested. The price is a larger forgetting radius, which follows a simple law in the writer's fan-in: forgetting 1% of turns erases 73.0% of derived memories with session-level summaries but only 3.8% with four-turn windows, which also answer better; re-deriving restores what is lost.

DOI
10.48550/arXiv.2611.18133 ↗
著者
Yulliwas Ameur, Billal Mokhtari, Samia Bouzefrane
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月13日
出版版
ソースのメタデータにリンクなし
AI エージェント87% 関連PDF原文を読む ↗
arXiv
プレプリントarXiv · Computer Science·2026/11/12

Where LLM Agents Get Stuck Debugging Databases: Access More Than Reasoning

Large language model (LLM) coding agents are increasingly asked not only to write code but to debug running systems from live runtime data. We report a field observation of one such agent (Claude Code) as it diagnosed eight database incidents in a production message-dispatch engine. In every incident whose root cause depended on runtime concurrency, the agent announced a cause, shipped a fix, and later walked it back, and each wrong guess cost a deploy-and-observe cycle. Mapping each incident to what the agent lacked, we find that access to production state was the most pervasive bottleneck. The missing access included live lock views, untruncated deadlock reports, read-only execution, and an explicit environment context. An access gap was present in all five concurrency-dependent incidents: alone in one, and in four combined with a reasoning error such as anchoring on an early cause, incomplete exploration of the configuration, or a misreading of the code's transaction semantics. The three incidents that did not depend on concurrency needed nothing beyond what the agent already had. Within the incidents, the agent's wrong hypotheses were consistent with the evidence it could see; they were not fabrications. We argue that the next step for production-debugging agents is a forensics layer that gives the agent the access it lacks inside existing security controls. Such a layer would combine a safe interrogation API, a lock-and-deadlock flight recorder, and a production replay harness.

DOI
10.48550/arXiv.2611.17304 ↗
著者
Gustavo Pinto
ジャーナル / 発表先
情報なし
出版物の種類
プレプリント
ステータス
プレプリント
公開日
2026年11月12日
出版版
ソースのメタデータにリンクなし
AI エージェント87% 関連PDF原文を読む ↗
ResearchRadar による提供結果の取得日時: 2026/11/16 19:00 UTC約15分ごとに更新
実際のレーダーを、気軽に。すべての原始論文を開き、ランク付けされた結果を見られます。保存、設定変更、デイリーブリーフの受信にだけアカウントが必要です。

このレーダーを自分のものにしますか?

トピック、クエリ、期間、ソースセットを編集できる状態で無料アカウントを作成します。

別のテンプレートを試す