Imagen de Portada

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Jiahao, Cheng, Fei, Jiang, Junfeng, Yu, Zefan, Aizawa, Akiko
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility
por: Huang, Jiahao, et al.
Publicado: (2026)

JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models
por: Jiang, Junfeng, et al.
Publicado: (2024)

InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
por: Wu, Yunze, et al.
Publicado: (2025)

GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents
por: Costarelli, Anthony, et al.
Publicado: (2024)

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
por: Wang, Ruipeng, et al.
Publicado: (2026)

DCA-Bench: A Benchmark for Dataset Curation Agents
por: Huang, Benhao, et al.
Publicado: (2024)

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
por: Shang, Yu, et al.
Publicado: (2025)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
por: Zhu, Yihua, et al.
Publicado: (2026)

TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
por: Xu, Hanwen, et al.
Publicado: (2025)

Harnessing PDF Data for Improving Japanese Large Multimodal Models
por: Baek, Jeonghun, et al.
Publicado: (2025)

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
por: Zhou, Yifan, et al.
Publicado: (2026)

VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
por: Xu, Zelai, et al.
Publicado: (2025)

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
por: Zheng, Tianshi, et al.
Publicado: (2025)

COMMA: A Communicative Multimodal Multi-Agent Benchmark
por: Ossowski, Timothy, et al.
Publicado: (2024)

Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
por: Dong, Haonan, et al.
Publicado: (2026)

TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
por: Cheng, Yu, et al.
Publicado: (2026)

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
por: Liu, Wenrui, et al.
Publicado: (2025)

TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
por: Mishra, Prakamya, et al.
Publicado: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
por: Zhang, Hanrong, et al.
Publicado: (2024)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
por: Yin, Sheng, et al.
Publicado: (2024)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
por: Tu, Xinming, et al.
Publicado: (2026)

T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning
por: Si, Yuehang, et al.
Publicado: (2025)

ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
por: Nguyen, Bang, et al.
Publicado: (2026)

PBT-Bench: Benchmarking AI Agents on Property-Based Testing
por: Jing, Lucas, et al.
Publicado: (2026)

AutoPenBench: Benchmarking Generative Agents for Penetration Testing
por: Gioacchini, Luca, et al.
Publicado: (2024)

GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
por: Yu, Bo, et al.
Publicado: (2026)

WritingBench: A Comprehensive Benchmark for Generative Writing
por: Wu, Yuning, et al.
Publicado: (2025)

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study
por: Kim, Kon Woo, et al.
Publicado: (2025)

SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes
por: Li, Kuan, et al.
Publicado: (2026)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
por: Lee, Seunghyun, et al.
Publicado: (2026)

JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees
por: Wang, Yuhui, et al.
Publicado: (2026)

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
por: Zheng, Qiaoyuan, et al.
Publicado: (2026)

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
por: Deng, Shihan, et al.
Publicado: (2024)

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
por: Jiang, Yixing, et al.
Publicado: (2025)

Eigenpruning: an Interpretability-Inspired PEFT Method
por: Vergara-Browne, Tomás, et al.
Publicado: (2024)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
por: Qiu, Jielin, et al.
Publicado: (2025)

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
por: Yu, Xinlei, et al.
Publicado: (2026)

MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
por: Zhang, Junkai, et al.
Publicado: (2025)

ProBench: Benchmarking GUI Agents with Accurate Process Information
por: Yang, Leyang, et al.
Publicado: (2025)

CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics
por: Liu, Junqi, et al.
Publicado: (2025)