Imagen de Portada

PA3: Policy-Aware Agent Alignment through Chain-of-Thought

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dipta, Shubhashis Roy, Bis, Daniel, Zhou, Kun, Wang, Lichao, Yao, Benjamin Z., Guo, Chenlei, Sarikaya, Ruhi
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition
por: Dipta, Shubhashis Roy, et al.
Publicado: (2025)

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
por: Sarwar, Nobin, et al.
Publicado: (2025)

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
por: Dipta, Shubhashis Roy, et al.
Publicado: (2026)

PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection
por: Hossan, Rakib, et al.
Publicado: (2025)

UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation
por: Dipta, Shubhashis Roy, et al.
Publicado: (2024)

HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?
por: Dipta, Shubhashis Roy, et al.
Publicado: (2024)

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
por: Dipta, Shubhashis Roy, et al.
Publicado: (2025)

BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects
por: Hasan, Jakir, et al.
Publicado: (2025)

Multimodal Policy Internalization for Conversational Agents
por: Wang, Zhenhailong, et al.
Publicado: (2025)

†DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems
por: Nazi, Zabir Al, et al.
Publicado: (2026)

Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
por: Lia, Nusrat Jahan, et al.
Publicado: (2026)

Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning
por: Xu, Ningning, et al.
Publicado: (2025)

DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
por: Dipta, Shubhashis Roy, et al.
Publicado: (2026)

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
por: Jiang, Yuxuan, et al.
Publicado: (2026)

VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis
por: Dipta, Shubhashis Roy, et al.
Publicado: (2025)

BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali
por: Hasan, Jakir, et al.
Publicado: (2026)

Analyzing and Internalizing Complex Policy Documents for LLM Agents
por: Liu, Jiateng, et al.
Publicado: (2025)

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
por: Nazi, Zabir Al, et al.
Publicado: (2026)

BanglaLlama: LLaMA for Bangla Language
por: Zehady, Abdullah Khan, et al.
Publicado: (2024)

Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought
por: Si, Jianfeng, et al.
Publicado: (2026)

Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation
por: Abdullah, Sharif Mohammad, et al.
Publicado: (2025)

Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles
por: Lia, Nusrat Jahan, et al.
Publicado: (2025)

WINELL: Wikipedia Never-Ending Updating with LLM Agents
por: Reddy, Revanth Gangi, et al.
Publicado: (2025)

HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
por: Zheng, Minghui, et al.
Publicado: (2026)

Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
por: Yao, Yao, et al.
Publicado: (2023)

Knowledge Editing through Chain-of-Thought
por: Wang, Changyue, et al.
Publicado: (2024)

Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment
por: Zhang, Yunfan, et al.
Publicado: (2025)

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
por: Waheed, Abdul, et al.
Publicado: (2025)

Enhancing Adversarial Attacks through Chain of Thought
por: Su, Jingbo
Publicado: (2024)

Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation
por: Qiu, Yuli, et al.
Publicado: (2024)

Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention
por: Nazi, Zabir Al, et al.
Publicado: (2026)

Chain-of-Thought Reasoning Without Prompting
por: Wang, Xuezhi, et al.
Publicado: (2024)

Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
por: Kim, Doyoung, et al.
Publicado: (2026)

Efficient Reasoning for LLMs through Speculative Chain-of-Thought
por: Wang, Jikai, et al.
Publicado: (2025)

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
por: Chen, Yiqun, et al.
Publicado: (2026)

ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
por: Hu, Minda, et al.
Publicado: (2026)

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
por: Cheng, Jeffrey, et al.
Publicado: (2024)

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
por: Jeung, Wonje, et al.
Publicado: (2025)

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
por: Dai, Chengwei, et al.
Publicado: (2024)

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
por: Zhu, Zihao, et al.
Publicado: (2025)