OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows
Abstract: Existing benchmarks for autonomous AI scientists evaluate only final outputs---generated code, hypotheses, or papers---yet discard the reasoning process by which those outputs were obtained. This makes it impossible to audit scientific methodology, diagnose failure modes, or distinguish systematic reasoning from fortunate guessing. We present \textbf{OpenDiscoveryTrace}, a public dataset of 558 complete AI scientific agent trajectories that captures how models reason, not just what they produce. Each trajectory records a structured 9-field-per-step trace---including thoughts, tool calls, observations, errors, revision triggers, and self-reported confidence---as models execute 124 scientific tasks spanning drug discovery, materials science, genomics, and scientific literature analysis. The dataset covers seven models: three frontier models (GPT-5.4, Claude Opus 4.6, and Gemini 3.1 Pro; 124 trajectories each, fully balanced across domains and difficulty levels) and four open-weight models (Qwen2.5-7B, Mistral-7B-v0.3, Phi-3.5-mini, and Qwen2.5-1.5B; 30 each), plus 60 live-retrieval variant trajectories. Pilot analysis on 363 LLM-judged trajectories reveals that process traces expose behavioral differences invisible to output-only evaluation: all three frontier models achieve comparable success rates (84--89%), yet Claude Opus 4.6 produces 30$\times$ more errors than GPT-5.4 (2.5 vs. 0.08 per trajectory, $p < 0.0001$, Cliff's $\delta = 0.613$), with qualitatively different error profiles---66.7% tool misuse for Claude versus 83.6% reasoning errors for GPT-5.4. We define five benchmark tasks with baselines from logistic regression, random forests, LSTMs, and Transformer models. The dataset, trace schema, agent harness, and benchmark definitions are publicly available under CC BY 4.0 to support research on process-level evaluation, scientific agent auditing, and AI governance.
Submission history
Access Paper:
Current browse context:
References & Citations
BibTeX formatted citation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Verified source · arXiv.org
Reported by arXiv.org. Open the original for full media and formatting.
More in Research
All newsDecision-Focused Active Learning for Scale-Aware Critical-Materials Recovery
Choosing a recovery process for scale-up requires connecting laboratory results with product requirements, process costs, and scale effects. We analyze records from Pacific Northwest National Laboratory's Computer Intelligence for Critical Element Recovery and Optimization (CICERO) workflow for autonomous selective precipitation. Active learning uses prior results to choose experiments. In a conditional retrospective benchmark with fitted models and recycled neodymium-iron-boron (NdFeB) magnet records, active learning finds the best recorded result with fewer experiments than nonadaptive spac…
Read at arXiv cs.AIGradland: On Phenomenal Experience, Differentiated Across Many Dimensions
This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions are (mostly) differentiable. The paper introduces two measures of Jacobian structure: effective rank and cohesion, based on Kirchhoff complexity. Applying the measures to a series of worked examples shows the hypothesis accounts for: (1) the duration of experience, that it can prolong over hundreds o…
Read at arXiv cs.AIAdaptive Entangled Game Modules in Artificial General Intelligence
We introduce a probability-wave framework for modeling the collective behavior of interacting adaptive agents, deriving testable eigenmodes through a generalized behavioral intelligence (GBI) nonlocal probability-wave equation. This framework captures a broad range of human intelligence behaviors with analytical mechanisms and offers an indirect method to examine the Liu-Chen-Ao (LCA) hypothesis of nonlocal entangled nerve fibers in the brain through collective trader behaviors. Our empirical analysis of Chinese intraday stock market data demonstrates that adaptive entangled game modes explai…
Read at arXiv cs.AIContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance
As LLM agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks acceptable even though the system skipped the check, branch, dependency, or invariant that made the answer justified. Output-only evaluation sees the answer, and trace-aware judging sees activity, but neither identifies which obligations were active for the query. We introduce CONTRACTEVAL, a diagnostic framework for making those active obligations explicit. It represents procedural instructions as query-active obligations and matches them aga…
Read at arXiv cs.AI