TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents
The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics like Pass@1, creating a "high-score illusion" that ignores the quality, efficiency, and soundness of the reasoning process; and 2) the failure of static benchmarks to quantify crucial attributes like robustness and latent capability. To address these gaps, we introduce TRACE (Trajectory-Aware Comprehensive Evaluation), a framework that holistically assesses the entire problem-solving trajectory. To counter the "high-score illusion", we propose a Hierarchical Trajectory Utility Function that quantifies process efficiency and cognitive quality, including evidence grounding, alongside accuracy. To measure deeper attributes, TRACE introduces a Scaffolded Capability Assessment protocol, quantifying an agent's latent ability by determining the minimum guidance needed for success. Our contributions include the TRACE framework, its novel metrics, and the accompanying DeepResearch-Bench with controllable complexity. Experiments show TRACE delivers a granular ranking that uncovers critical trade-offs between agent accuracy, efficiency, and robustness entirely missed by singular metrics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation, obscuring intermediate hallucinations that accumulate throughout t…
TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly on global image understanding, strug…
Trajectory PredictionScene UnderstandingLogical ReasoningTRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level or short-context detectors struggle to re…
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning: they inspect pipeline outputs rather than shaping the deliberation…
Adversarial RobustnessTRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-…
Text Generation