Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking

Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy AI-enabled scientific workflows. Existing approaches often use LLMs as judges or rely on semantic similarity, which can favor familiar ideas over novel ones. We propose a logit-based energy scoring method that evaluates hypotheses using a language model's intrinsic confidence rather than comparative judgment. We benchmarked seven language models on 1,323 papers across 12 disciplines. Each paper was paired with its hypothesis and fifteen incorrect alternatives. Intrinsic scoring reached 33.0% Hit@1 pooled across both scorers, compared with 16.6% for prompted listwise ranking. The strongest configuration, a 1-billion-parameter model using logit-based energy scoring, reached 53.1%, though this was the maximum across 14 model-by-scorer combinations selected post hoc. Overall, intrinsic model confidence shows potential for scientific hypothesis evaluation. This study also motivates future research on confidence-based methods for trustworthy AI-enabled scientific discovery.

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fundamental challenges for AI systems: the relationships across representations are inherently \textit{one-to-many}, supervision is ambiguous and costly, and model optimization lacks a principled signal that is both direction-adaptive and representation-generalizable beyond task-specific objectives. We introduce CoCoEvolve to improve consistency across chart, table, and code representations. Instead of treating cross-representation mapping as a one-to-many problem, we define explicit one-to-one correspondences and optimize models using agreement between representations, without additional annotations. During training, CoCoEvolve@Train performs co-evolution across the chart-table-code cycle, while CoCoEvolve@Test applies the same consistency objective at inference time for test-time co-optimization. We also present CoCoEvolve@Eval, an evaluation suite covering all six cross-representation tasks. Across four benchmarks, CoCoEvolve improves performance in both training-time and test-time settings. Our project page: https://xhguo7.github.io/CoCoEvolve/.

Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation

AI co-scientists can generate fluent materials-science hypotheses, but fluency does not show that an answer preserves a scientifically meaningful mechanism. We present a graph-to-answer mechanism-tracing case study for Graph-PRefLexOR-8B, a Qwen3-8B model adapted to expose distinct stages for brainstorming, graph construction, pattern extraction, and synthesis. We organize semantic backtracking, graph corruption, activation-based recovery measurements, and layer-by-token-region grids into a visual diagnostic workflow for inspecting this pathway. Across 100 open-ended materials-science questions, final answers remain closest to the model's own structured stages, especially synthesis. Under graph corruption, a full sweep over 37 residual-stream checkpoints, the embedding output and 36 transformer blocks, shows little mechanism recovery in the earlier transition region at layers 7--10, recovery instead concentrates in late synthesis and answer-start regions around layers 30 and 36. The workflow is intended to help scientists and model developers identify where a generated hypothesis loses or regains mechanism support before it is passed to downstream experimental planning.

Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap

One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than anticipated. Multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field. Producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. We update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18), and scope the path forward to a two-year horizon. The first year concentrates on interfaces, protocol adoption, and the scaffolding of verification, and the second targets federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo.

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceable responses to open-ended materials design problems, making it difficult to determine whether final answers are supported by coherent intermediate reasoning. We develop Graph-PRefLexOR, a family of graph-native reasoning models fine-tuned with Group Relative Policy Optimization (GRPO) to organize reasoning into explicit phases for mechanism exploration, graph construction, pattern extraction, and hypothesis synthesis. This design links neural language generation with symbolic relational structure, enabling causal connections to be constructed, inspected, and reused. On 100 open-ended questions from materials science and mechanics literature, Graph-PRefLexOR achieves 40-65% improvements over corresponding base models, with the largest gains in reasoning traceability. Embedding analyses show broader semantic exploration and approximately 2-3 times greater semantic diversity than baselines. Semantic backtracking and layer-wise hidden-state analyses further show stronger alignment between structured reasoning and final answers. Finally, test-time graph expansion reveals that additional compute primarily increases long-range conceptual recombination within a bounded semantic space, rather than simply expanding semantic coverage. These results establish graph-native reinforcement learning as a pathway toward interpretable AI systems for scientific hypothesis generation in materials design and other scientific applications.

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue-multi-agent, multi-turn interactions improves the quality of NLP- based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing an empirical evidence for dialogue-driven hazard analysis.

Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams

Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through dense spatial layouts, domain-specific symbols, and cross-references between visual callouts and structured parts tables. Despite their centrality to service, repair, and design workflows, there is no public benchmark for measuring VLM capabilities in this domain; existing datasets primarily focus on flowcharts, scientific figures, or business documents. To address this gap, we introduce Enginuity, the first open dataset and benchmark for evaluating VLMs on complex engineering diagrams. We define two tasks over a corpus of U.S. military service and repair manuals: structured parts-table extraction (Task 1) and free-form visual diagram question answering (VQA)(Task 2) for benchmarking. We evaluate four frontier VLMs (GPT-5.2 Chat, Claude Opus 4.7, Gemma 4, Qwen3-VL-32B-Instruct) under zero-shot and chain-of-thought prompting. On Task 1, models reach Recall@all of 0.61-0.87 but Token F1pen of only 0.03-0.18, exposing a systematic gap between part identification and description fidelity. Task 2 reveals a consistent factual-reasoning gap across all models. A supporting analysis shows that token-overlap metrics under-report model capability on technical descriptions by 2-6x relative to semantic similarity, motivating LLM-as-judge calibration for domain-specific evaluation. We release the dataset, annotations, evaluation harness, and per-sample model outputs to support a reproducible study of VLM capability on engineering content.

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?

Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generated hypotheses. We study KG-guided hypothesis generation for battery materials across Mistral-7B, Llama-3.1-70B, and Gemini 2.5 Flash. We perturb local KGs by varying density, ontology richness, topology, and control structure, and evaluate outputs with both provided-graph and fixed-reference metrics. Across models, KG utility is selective and model-dependent: graph context changes outputs, but no-KG outputs also recover substantial graph content from model priors. Compact top-k subgraphs often approximate full-KG behavior, including when claimed-outcome triples are held out. At the same time, compression is not unique to one semantic ranking rule, random and topology-based subsets can also recover much of the signal. These results support a redundancy-aware Compressive KG hypothesis: useful KG signal is often recoverable from compact, scientifically structured subgraphs rather than requiring the full local graph.

Predicting New Concept-Object Associations in Astronomy by Mining the Literature

We construct a concept-object knowledge graph from the full astro-ph corpus through July 2025. Using an automated pipeline, we extract named astrophysical objects from OCR-processed papers, resolve them to SIMBAD identifiers, and link them to scientific concepts annotated in the source corpus. We then test whether historical graph structure can forecast new concept-object associations before they appear in print. Because the concepts are derived from clustering and therefore overlap semantically, we apply an inference-time concept-similarity smoothing step uniformly to all methods. Across four temporal cutoffs on a physically meaningful subset of concepts, an implicit-feedback matrix factorization model (alternating least squares, ALS) with smoothing outperforms the strongest neighborhood baseline (KNN using text-embedding concept similarity) by 16.8% on NDCG@100 (0.144 vs 0.123) and 19.8% on Recall@100 (0.175 vs 0.146), and exceeds the best recency heuristic by 96% and 88%, respectively. These results indicate that historical literature encodes predictive structure not captured by global heuristics or local neighborhood voting, suggesting a path toward tools that could help triage follow-up targets for scarce telescope time.

BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents

Decades of engineering drawings and technical records remain locked in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. We present Blueprint, a layout-aware multimodal retrieval system designed for large-scale engineering repositories. Blueprint detects canonical drawing regions, applies region-restricted VLM-based OCR, normalizes identifiers (e.g., DWG, part, facility), and fuses lexical and dense retrieval with a lightweight region-level reranker. Deployed on ~770k unlabeled files, it automatically produces structured metadata suitable for cross-facility search. We evaluate Blueprint on a 5k-file benchmark with 350 expert-curated queries using pooled, graded (0/1/2) relevance judgments. Blueprint delivers a 10.1% absolute gain in Success@3 and an 18.9% relative improvement in nDCG@3 over the strongest vision-language baseline}, consistently outperforming across vision, text, and multimodal intents. Oracle ablations reveal substantial headroom under perfect region detection and OCR. We release all queries, runs, annotations, and code to facilitate reproducible evaluation on legacy engineering archives.