When Is Enough Not Enough? Illusory Completion in Search Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ko, Dayoon, Kim, Jihyuk, Kim, Sohyeon, Park, Haeju, Lee, Dahyun, Kim, Gunhee, Lee, Moontae, Lee, Kyungjae
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
di: Ko, Dayoon, et al.
Pubblicazione: (2025)

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
di: Kim, Jinyoung, et al.
Pubblicazione: (2024)

When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR
di: Ko, Dayoon, et al.
Pubblicazione: (2025)

Shifting from Ranking to Set Selection for Retrieval Augmented Generation
di: Lee, Dahyun, et al.
Pubblicazione: (2025)

Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
di: Lee, Kyungjae, et al.
Pubblicazione: (2024)

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

Can Language Models Laugh at YouTube Short-form Videos?
di: Ko, Dayoon, et al.
Pubblicazione: (2023)

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
di: Ahn, Jaewoo, et al.
Pubblicazione: (2025)

Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMs
di: Kim, Hyeonwoo, et al.
Pubblicazione: (2024)

Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models
di: Kim, Dahyun, et al.
Pubblicazione: (2024)

Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark
di: Park, Chanjun, et al.
Pubblicazione: (2024)

Policy-labeled Preference Learning: Is Preference Enough for RLHF?
di: Cho, Taehyun, et al.
Pubblicazione: (2025)

Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models
di: Park, Hyunbyung, et al.
Pubblicazione: (2024)

1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models
di: Park, Chanjun, et al.
Pubblicazione: (2024)

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech
di: Woo, Sang Hoon, et al.
Pubblicazione: (2025)

GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?
di: Ko, Dayoon, et al.
Pubblicazione: (2024)

EXAONE 3.0 7.8B Instruction Tuned Language Model
di: An, Soyoung, et al.
Pubblicazione: (2024)

KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR
di: Kim, Hajung, et al.
Pubblicazione: (2024)

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism
di: Park, Chanjun, et al.
Pubblicazione: (2024)

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
di: Kim, Jiyeon, et al.
Pubblicazione: (2026)

CaRT: Teaching LLM Agents to Know When They Know Enough
di: Liu, Grace, et al.
Pubblicazione: (2025)

Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
di: Khalifa, Muhammad, et al.
Pubblicazione: (2026)

Evalverse: Unified and Accessible Library for Large Language Model Evaluation
di: Kim, Jihoo, et al.
Pubblicazione: (2024)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
di: Lee, Joosung, et al.
Pubblicazione: (2026)

Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
di: Kim, Wonjoong, et al.
Pubblicazione: (2025)

sDPO: Don't Use Your Data All at Once
di: Kim, Dahyun, et al.
Pubblicazione: (2024)

A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist
di: Jeon, Sohyeon, et al.
Pubblicazione: (2025)

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
di: Kim, Serin, et al.
Pubblicazione: (2026)

Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
di: Lee, Seungyoon, et al.
Pubblicazione: (2024)

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
di: Kim, Dahyun, et al.
Pubblicazione: (2023)

Screening Is Enough
di: Nakanishi, Ken M.
Pubblicazione: (2026)

KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs
di: Kim, Haechan, et al.
Pubblicazione: (2026)

Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation
di: Kim, Wongyu, et al.
Pubblicazione: (2025)

Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning
di: Lee, Gisang, et al.
Pubblicazione: (2024)

Learning When to Translate for Multilingual Reasoning
di: Kang, Deokhyung, et al.
Pubblicazione: (2026)

When Less is Enough: Efficient Inference via Collaborative Reasoning
di: Chen, Yilei, et al.
Pubblicazione: (2026)

Single Ground Truth Is Not Enough: Adding Flexibility to Aspect-Based Sentiment Analysis Evaluation
di: Yang, Soyoung, et al.
Pubblicazione: (2024)

Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
di: Kim, Taehun, et al.
Pubblicazione: (2026)

When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English
di: Biyik, Hasan Can, et al.
Pubblicazione: (2026)

Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
di: Ban, Minjeong, et al.
Pubblicazione: (2026)