ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “context reliability”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CLcs.AIcs.LGRecentMay 28, 2026

The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability

Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei, Ziwei Dong +2 more

The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…

View →
cs.AIRecentMay 29, 2026

Learning Agent-Compatible Context Management for Long-Horizon Tasks

Lu Yi, Runlin Lei, Liuyi Yao, Yuexiang Xie +5 more

The paper introduces Adaptive Context Management (AdaCoM), an external context manager that uses reinforcement learning to improve the performance of frozen LLM agents on long-horizon tasks by intelli…

View →
cs.CLEmpiricalRecentOct 19, 2026

KEEP-Bench: Evaluating Evidence Preservation in Context Compression

Ziqing Man, Di Wu, Jia-Chen Gu, Junyi Zhang +2 more

The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.

View →
cs.AIRecentMay 27, 2026

When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

Dasol Choi, Alex Kwon

The paper introduces 'brittle safety,' a failure mode where aligned language models fail to adapt their safety behavior when a situational context changes, and proposes state-aware validation to detec…

View →
cs.CRcs.CLApr 23, 2026

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin +4 more

The paper introduces CI-Work, a benchmark demonstrating that current enterprise LLM agents frequently leak sensitive information while performing tasks, suggesting that privacy protection requires arc…

View →
cs.CLcs.AIEmpiricalRecentJun 26, 2026

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

Sambaran Bandyopadhyay

This paper tests the assumption that evaluation is easier than generation in LLM-as-a-Judge and self-evaluation pipelines using a controlled in-context QA setting and reveals that evaluation attends t…

View →
cs.AIcs.LGEmpiricalRecentOct 22, 2026

EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence

Qijin Zhang, Hanzhen Wang, Yuehan Zhao, Haoyu Dai +3 more

This paper introduces a benchmark for evaluating the safety of language model agents under missing evidence.

View →
cs.CLcs.IRRecentMay 29, 2026

Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

Han Zhang, Zihao Tang, Xin Yu, Xiao Liu +7 more

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

View →
cs.AIcs.MAEmpiricalRecentJun 22, 2026

RaMem: Contextual Reinstatement for Long-term Agentic Memory

Wei Yang, Bryce Kan, Shixuan Li, Li Li +4 more

The paper proposes a framework called RaMem to improve the validity of retrieved memories in long-term memory systems for LLM agents.

View →
cs.AIRecentJun 1, 2026

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Jiaming Wang, Ziteng Feng, Jiangtao Wu, Ruihao Li +7 more

The paper introduces TELBench and the DRIFT framework to enable fine-grained, span-level error localization in deep-research agents, significantly improving the ability to pinpoint exactly where an ag…

View →
cs.CLcs.LGRecentMay 30, 2026

Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models

S M Tahmid Siddiqui, Akib Jawad Ononto, Anoop Singhal, Latifur Khan

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

View →
cs.CRcs.CLcs.CYMay 17, 2026

AI Agents May Always Fall for Prompt Injections

Sahar Abdelnabi, Eugene Bagdasarian

The paper argues that prompt injection is a fundamental vulnerability in AI agents, proposing that Contextual Integrity (CI) offers a principled framework to understand and mitigate context-sensitive…

View →
cs.CRMay 2, 2026

Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly

Igor Santos-Grueiro

The paper identifies and measures a critical failure mode where LLM agents violate policies by losing or corrupting directive-bearing state during the process of assembling the decision context, and p…

View →
cs.AIRecentMay 30, 2026

KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning

Jayant Parashar, Suchendra M. Bhandarkar

KACE introduces a novel knowledge-adaptive context engineering framework that separates knowledge storage from usage, significantly improving mathematical reasoning accuracy on challenging benchmarks…

View →
eess.AScs.CLEmpiricalRecentJun 17, 2026

IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages

Sakshi Joshi, Dhruv Subhash Rathi, Sanskar Singh, Eldho Ittan George +3 more

The paper introduces IndicContextEval, a multilingual benchmark to evaluate the use of contextual signals in AudioLLMs.

View →
cs.CLcs.SEEmpiricalRecentJun 24, 2026

Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability

Yang Tian, Zhengpeng Shi, Bo Zhao

ToolBench-X is a benchmark for evaluating agents under recoverable reliability hazards

View →