Buchumschlag

Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chae, Hyungjoo, Kim, Yeonghyeon, Kim, Seungone, Ong, Kai Tzu-iunn, Kwak, Beong-woo, Kim, Moohyeon, Kim, Seonghwan, Kwon, Taeyoon, Chung, Jiwan, Yu, Youngjae, Yeo, Jinyoung
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations
von: Ong, Kai Tzu-iunn, et al.
Veröffentlicht: (2024)

Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code
von: Chae, Hyungjoo, et al.
Veröffentlicht: (2024)

ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions
von: Kwak, Beong-woo, et al.
Veröffentlicht: (2025)

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
von: Kim, Sunghwan, et al.
Veröffentlicht: (2026)

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
von: Kim, Sunghwan, et al.
Veröffentlicht: (2025)

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
von: Lee, Seungbeen, et al.
Veröffentlicht: (2024)

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
von: Chae, Hyungjoo, et al.
Veröffentlicht: (2024)

Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
von: Kwon, Taeyoon, et al.
Veröffentlicht: (2025)

Towards Lifelong Dialogue Agents via Timeline-based Memory Management
von: Ong, Kai Tzu-iunn, et al.
Veröffentlicht: (2024)

One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL
von: Chae, Hyungjoo, et al.
Veröffentlicht: (2025)

Evaluating Robustness of Reward Models for Mathematical Reasoning
von: Kim, Sunghwan, et al.
Veröffentlicht: (2024)

Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback
von: Moon, Seungjun, et al.
Veröffentlicht: (2023)

LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study
von: Yang, Dongil, et al.
Veröffentlicht: (2025)

VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models
von: Kim, Seoyeon, et al.
Veröffentlicht: (2024)

Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
von: Kim, Hana, et al.
Veröffentlicht: (2024)

Can You Share Your Story? Modeling Clients' Metacognition and Openness for LLM Therapist Evaluation
von: Kim, Minju, et al.
Veröffentlicht: (2025)

Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset
von: Kim, Minjin, et al.
Veröffentlicht: (2024)

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
von: Chae, Hyungjoo, et al.
Veröffentlicht: (2025)

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
von: Kang, Dongjin, et al.
Veröffentlicht: (2024)

Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales
von: Kwon, Taeyoon, et al.
Veröffentlicht: (2023)

PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
von: Kim, Namyoung, et al.
Veröffentlicht: (2025)

Towards Direct Evaluation of Harness Optimizers via Priority Ranking
von: Ong, Kai Tzu-iunn, et al.
Veröffentlicht: (2026)

Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education
von: Kim, Seungyoon, et al.
Veröffentlicht: (2024)

Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance
von: Choi, Dongwook, et al.
Veröffentlicht: (2025)

Teaching Metric Distance to Discrete Autoregressive Language Models
von: Chung, Jiwan, et al.
Veröffentlicht: (2025)

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
von: Kim, Youngmin, et al.
Veröffentlicht: (2025)

Dynamics of Socio-Institutional Asynchrony in Generative AI: Analyzing the Relative Importance of Intervention Timing vs. Enforcement Efficiency via the Socio-Institutional Asynchrony Model (SIAM)
von: Kim, Taeyoon
Veröffentlicht: (2025)

DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
von: Han, Hojae, et al.
Veröffentlicht: (2026)

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
von: Seo, Yeongbin, et al.
Veröffentlicht: (2025)

PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints
von: Park, Minjun, et al.
Veröffentlicht: (2026)

v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning
von: Chung, Jiwan, et al.
Veröffentlicht: (2025)

EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
von: Choi, Dongwook, et al.
Veröffentlicht: (2026)

KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context
von: Wang, Xiaonan, et al.
Veröffentlicht: (2024)

Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
von: Ko, Sungho, et al.
Veröffentlicht: (2024)

Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
von: Hwang, Hyeonbin, et al.
Veröffentlicht: (2024)

FREESON: Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
von: Kim, Chaeeun, et al.
Veröffentlicht: (2025)

PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent
von: Cui, Yuxin, et al.
Veröffentlicht: (2026)

Floquet Chern Insulators and Radiation-Induced Zero Resistance in Irradiated Graphene
von: Kim, Youngjae, et al.
Veröffentlicht: (2025)

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation
von: Lee, Seongyun, et al.
Veröffentlicht: (2024)

Inside Back Cover: Light‐Induced Chemiluminescence Microscopy for Imaging Heterogeneous Photo‐Fenton‐Type Activity on Individual Hematite Photocatalysts (Angew. Chem. Int. Ed. 49/2025)
von: Taeyoon Kim, et al.
Veröffentlicht: (2025)