Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction

• URL: http://arxiv.org/abs/2602.02455v1
• Date: Mon, 02 Feb 2026 18:46:16 GMT
• Title: Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
• Abstract summary: textbfDrift-Bench is the first diagnostic benchmark that evaluates agentic pragmatics under input faults.<n>Method bridges clarification research and agent safety evaluation, enabling systematic diagnosis of failures that can lead to unsafe executions.
• Score: 20.610305266852638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models transition to autonomous agents, user inputs frequently violate cooperative assumptions (e.g., implicit intent, missing parameters, false presuppositions, or ambiguous expressions), creating execution risks that text-only evaluations do not capture. Existing benchmarks typically assume well-specified instructions or restrict evaluation to text-only, single-turn clarification, and thus do not measure multi-turn disambiguation under grounded execution risk. We introduce \textbf{Drift-Bench}, the first diagnostic benchmark that evaluates agentic pragmatics under input faults through multi-turn clarification across state-oriented and service-oriented execution environments. Grounded in classical theories of communication, \textbf{Drift-Bench} provides a unified taxonomy of cooperative breakdowns and employs a persona-driven user simulator with the \textbf{Rise} evaluation protocol. Experiments show substantial performance drops under these faults, with clarification effectiveness varying across user personas and fault types. \MethodName bridges clarification research and agent safety evaluation, enabling systematic diagnosis of failures that can lead to unsafe executions.

Related papers

• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Operational Hallucination and Safety Drift in AI Agents [0.3823356975862005]
  Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.<n>This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift and Operational Hallucination.<n>We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, state tracking, and forced termination primitives.
  arXiv  Detail & Related papers  (2026-07-20T17:01:50Z)
• Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity [0.0]
  This paper introduces adversarial pragmatics as a benchmark for evaluating model behaviour under instruction conflict, embedded commands, quotation, scope ambiguity, deixis, indirect speech acts, and multi-turn agent transcripts.<n>The contribution is empirical and methodological: a linguistically controlled taxonomy, an 18-item seed benchmark with validator-enforced metadata, a 54-row local seed pilot, an expert-evaluation protocol distinguishing task success, policy compliance, safety risk, refusal outcome, and evaluator confidence, and metrics for judge validity, diagnostic ambiguity, and taxonomy drift.
  arXiv  Detail & Related papers  (2026-07-01T16:33:14Z)
• Controllable User Simulation [41.65602738642653]
  This work formalizes controllable simulation as a causal inference problem.<n>We show that the standard practice of training simulators via supervised fine-tuning on post-hoc trajectory labels yields a structurally biased model.<n>We propose practical training mitigations: a priori controls, step-wise dynamic controls, and direct policy-conditioned learning.
  arXiv  Detail & Related papers  (2026-05-12T04:44:29Z)
• Efficient Agent Evaluation via Diversity-Guided User Simulation [7.723545220477047]
  DIVERT is a snapshot-based, coverage-guided user simulation framework for systematic exploration of agent-user interactions.<n>It captures the full agent-environment state at critical decision points and resumes execution from these snapshots.<n>By focusing evaluation on semantically diverse and underexplored trajectories, DIVERT improves both efficiency and coverage.
  arXiv  Detail & Related papers  (2026-04-23T09:41:21Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI [45.21562889170875]
  We propose a systematic evaluation paradigm that characterizes agent trustworthiness over a scenario manifold.<n>The framework integrates four complementary components: static cognitive and policy analysis, (ii) interactive sandbox simulation, (iii) social-ethical alignment assessment, and (iv) a distribution-aware representative sampling engine.
  arXiv  Detail & Related papers  (2026-03-16T08:51:33Z)
• CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents [27.35968236632966]
  LLM-based code interpreter agents are increasingly deployed in critical situations.<n>Existing benchmarks fail to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context.<n>We introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation.
  arXiv  Detail & Related papers  (2026-02-23T06:41:41Z)
• The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI [0.0]
  This paper introduces a novel auditing framework to quantify latent trait estimation under ordinal uncertainty.<n>The research audits nine leading models across dimensions including Optimization Bias, Sycophancy, and Status-Quo Legitimization.
  arXiv  Detail & Related papers  (2026-02-19T06:56:01Z)
• The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation [11.984098021215878]
  We introduce the Semantic-Preserving Adrial Code Injection (SPACI) Framework and the Abstract Syntax Tree-Aware Semantic Injection Protocol (AST-ASIP)<n>These methods exploit the Syntax-Semantics Gap by embedding adversarial directives into syntactically inert regions (trivia nodes) of the Abstract Syntax Tree.<n>Through a large-scale evaluation of 9 SOTA models across 25,000 submissions in Python, C, C++, and Java, we reveal catastrophic failure rates (>95%) in high-capacity open-weights models like DeepSeek-V3.
  arXiv  Detail & Related papers  (2026-01-29T07:40:58Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs [10.896368527058714]
  Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries.<n>We introduce two comprehensive benchmarks: the Exaggerated Safety Benchmark (XSB) for single-turn prompts, annotated with "Focus" keywords that identify refusal-inducing triggers, and the Multi-turn Scenario-based Exaggerated Safety Benchmark (MS-XSB)<n>Our benchmarks reveal that exaggerated refusals persist across diverse recent LLMs and are especially pronounced in complex, multi-turn scenarios.
  arXiv  Detail & Related papers  (2025-10-09T12:38:16Z)
• D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models [62.83226685925107]
  Deceptive Reasoning Exposure Suite (D-REX) is a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output.<n>Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought.<n>We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms.
  arXiv  Detail & Related papers  (2025-09-22T15:59:40Z)
• A Novel Generative Model with Causality Constraint for Mitigating Biases in Recommender Systems [20.672668625179526]
  Latent confounding bias can obscure the true causal relationship between user feedback and item exposure.<n>We propose a novel generative framework called Latent Causality Constraints for Debiasing representation learning in Recommender Systems.
  arXiv  Detail & Related papers  (2025-05-22T14:09:39Z)
• Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework [17.91981142492207]
  We introduce AUGMENT, a framework for generating controlled paraphrases grounded in user behaviors.<n>AUGMENT leverages linguistically informed rules and enforces quality through checks on instruction adherence, semantic similarity, and realism.<n>Case studies show that controlled paraphrases uncover systematic weaknesses that remain obscured under unconstrained variation.
  arXiv  Detail & Related papers  (2025-05-06T14:17:30Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding [118.75567341513897]
  Existing methods typically analyze target text in isolation or solely with non-member contexts.<n>We propose Con-ReCall, a novel approach that leverages the asymmetric distributional shifts induced by member and non-member contexts.
  arXiv  Detail & Related papers  (2024-09-05T09:10:38Z)
• Debiasing Recommendation by Learning Identifiable Latent Confounders [49.16119112336605]
  Confounding bias arises due to the presence of unmeasured variables that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. We propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables to resolve the aforementioned non-identification issue.
  arXiv  Detail & Related papers  (2023-02-10T05:10:26Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.