Cover Image

The Amazing Agent Race: Strong Tool Users, Weak Navigators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Zae Myung, Lee, Dongseok, Kim, Jaehyung, Raheja, Vipul, Kang, Dongyeop
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Benchmarking Cognitive Biases in Large Language Models as Evaluators
by: Koo, Ryan, et al.
Published: (2023)

Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs
by: Kim, Zae Myung, et al.
Published: (2024)

Align to Structure: Aligning Large Language Models with Structural Information
by: Kim, Zae Myung, et al.
Published: (2025)

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
by: Kim, Zae Myung, et al.
Published: (2025)

Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
by: Lee, Minhwa, et al.
Published: (2024)

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output
by: Mooney, James, et al.
Published: (2026)

Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
by: Mooney, James, et al.
Published: (2025)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
by: Kim, Dongyoung, et al.
Published: (2024)

Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
by: Kwak, Minseo, et al.
Published: (2026)

Few-shot Personalization of LLMs with Mis-aligned Responses
by: Kim, Jaehyung, et al.
Published: (2024)

Learning to Correct for QA Reasoning with Black-box LLMs
by: Kim, Jaehyung, et al.
Published: (2024)

Training-free LLM Verification via Recycling Few-shot Examples
by: Lee, Dongseok, et al.
Published: (2025)

Becoming Experienced Judges: Selective Test-Time Learning for Evaluators
by: Jwa, Seungyeon, et al.
Published: (2025)

When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
by: Jeong, Soyeong, et al.
Published: (2025)

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
by: Kim, Suji, et al.
Published: (2026)

SelectLLM: Can LLMs Select Important Instructions to Annotate?
by: Parkar, Ritik Sachin, et al.
Published: (2024)

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
by: Kim, Dongseok, et al.
Published: (2025)

A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting
by: Gan, Shuyu, et al.
Published: (2025)

Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation
by: Park, Jong Inn, et al.
Published: (2025)

Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
by: Lim, Junghwan, et al.
Published: (2025)

Weak-to-Strong Elicitation via Mismatched Wrong Drafts
by: Deng, Wei
Published: (2026)

Bayesian WeakS-to-Strong from Text Classification to Generation
by: Cui, Ziyun, et al.
Published: (2024)

BAID: A Benchmark for Bias Assessment of AI Detectors
by: Basu, Priyam, et al.
Published: (2025)

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
by: Gwak, Minju, et al.
Published: (2026)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
by: Kim, Jeonghye, et al.
Published: (2025)

AutoFlow: Automated Workflow Generation for Large Language Model Agents
by: Li, Zelong, et al.
Published: (2024)

On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
by: Fan, Chenghao, et al.
Published: (2024)

SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
by: Kim, Jaehyung, et al.
Published: (2024)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
by: Kang, Minjae, et al.
Published: (2026)

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

Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
by: Kim, Jaekyeom, et al.
Published: (2024)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
by: Kang, Deokhyung, et al.
Published: (2025)

Scaling Unverifiable Rewards: A Case Study on Visual Insights
by: Gan, Shuyu, et al.
Published: (2025)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
by: Cui, Yingqian, et al.
Published: (2026)

Under the Surface: Tracking the Artifactuality of LLM-Generated Data
by: Das, Debarati, et al.
Published: (2024)

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
by: Qian, Cheng, et al.
Published: (2026)

UserBench: An Interactive Gym Environment for User-Centric Agents
by: Qian, Cheng, et al.
Published: (2025)

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
by: Chen, Zixiang, et al.
Published: (2024)

MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models
by: Kim, Junmo, et al.
Published: (2025)

Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction
by: Tsaknakis, Ioannis, et al.
Published: (2025)