Cover Image

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aluru, Aayush, Malik, Myra, Patankar, Samarth, Kim, Spencer, Zhu, Kevin, O'Brien, Sean, Sharma, Vasu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
by: Lu, Leo, et al.
Published: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
by: Gupta, Abhay, et al.
Published: (2025)

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
by: Csizmadia, Daniel, et al.
Published: (2025)

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods
by: Agarwal, Mrinal, et al.
Published: (2025)

Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT
by: Do, Timothy, et al.
Published: (2025)

ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
by: Khalid, Haziq Mohammad, et al.
Published: (2025)

CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
by: Rufail, Andrew, et al.
Published: (2025)

TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models
by: Liu, Joshua, et al.
Published: (2025)

Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks
by: Yugeswardeenoo, Dharunish, et al.
Published: (2024)

COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark
by: Chintapatla, Ishant, et al.
Published: (2025)

Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
by: Xiong, Lang, et al.
Published: (2025)

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration
by: Begin, James, et al.
Published: (2025)

Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning
by: Baek, Shaun, et al.
Published: (2025)

Causal Language Control in Multilingual Transformers via Sparse Feature Steering
by: Chou, Cheng-Ting, et al.
Published: (2025)

Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact
by: Nandan, Advey, et al.
Published: (2025)

Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation
by: Le, Duy, et al.
Published: (2025)

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs
by: Yu, Stanley, et al.
Published: (2025)

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction
by: Jiao, Zhengbo, et al.
Published: (2026)

The Geometry of Harmfulness in LLMs through Subconcept Probing
by: Shah, McNair, et al.
Published: (2025)

Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
by: Said, Muna Numan, et al.
Published: (2025)

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered
by: Mirza, Imran, et al.
Published: (2025)

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language
by: C, Jesus Alvarez, et al.
Published: (2025)

Interpreting the Latent Structure of Operator Precedence in Language Models
by: Yugeswardeenoo, Dharunish, et al.
Published: (2025)

Maternal and early life exposure induced AD‐ like pathophysiology and its mitigation by allicin
by: Aluru Parithathvi
Published: (2025)

MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization
by: Zhang, Jian, et al.
Published: (2025)

SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive Programming
by: Singh, Adhyayan Veer, et al.
Published: (2025)

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
by: Knappe, Tim, et al.
Published: (2024)

PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
by: Bae, Yubeen, et al.
Published: (2025)

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models
by: Shim, Jay, et al.
Published: (2024)

Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
by: Li, Jason, et al.
Published: (2025)

Improving LLM Abilities in Idiomatic Translation
by: Donthi, Sundesh, et al.
Published: (2024)

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning
by: Kim, Minwu, et al.
Published: (2025)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution
by: Wang, Shaobo, et al.
Published: (2025)

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark
by: Gupta, Abhay, et al.
Published: (2024)

Ultrafast Superconducting Qubit Readout with the Quarton Coupler
by: Ye, Yufeng, et al.
Published: (2024)

From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models
by: Chhua, Kaylee, et al.
Published: (2024)

Large Language Model Agent for Modular Task Execution in Drug Discovery
by: Ock, Janghoon, et al.
Published: (2025)

Interactive Distillation for Cooperative Multi-Agent Reinforcement Learning
by: Cho, Minwoo, et al.
Published: (2026)