Large language models exhibit non-negligible risks of generating policy-violating content, underscoring the need for effective and timely guardrail mechanisms. Existing streaming safety monitoring approaches enable detection during decoding, but still lack a reliable mechanism for deciding when to terminate generation, limiting their ability to act on early risk signals that are often sparse and unstable under partial observability. In response, we propose LTS, a token-level framework that explicitly learns a stopping criterion for preemptive early termination. LTS introduces a risk-aware STOP head for token-level risk assessment and leverages temporally structured supervision with multiscale evidence to model the evolution of safety risks during generation. By casting streaming safety monitoring as a constrained online stopping task and incorporating exponential moving average temporal aggregation, LTS enables reliable translation of emerging risk evidence into stable and timely termination decisions. LTS achieves an F1 score of 95.5% and is able to terminate harmful content at 13% of the generated sequence, substantially outperforming existing methods during early generation. In realistic streaming settings, it achieves around 90% token reduction.

Large Language Models (LLMs) are accelerating scientific idea generation, but rigorously evaluating these numerous, often superficial, AI-generated propositions for novelty and factual accuracy is a critical bottleneck; manual verification is too slow. Existing validation methods are inadequate: LLMs as standalone verifiers may hallucinate and lack domain knowledge (our findings show ~60% unawareness of relevant papers in specific domains), while traditional citation networks lack explicit causality and narrative surveys are unstructured. This underscores a core challenge: the absence of structured, verifiable, and causally-linked historical data of scientific evolution. To address this, we introduce THE-Tree (Technology History Evolution Tree), a computational framework that constructs such domain-specific evolution trees from scientific literature. THE-Tree employs a search algorithm to explore evolutionary paths. During its node expansion, it utilizes a novel "Think-Verbalize-Cite-Verify" process: an LLM proposes potential advancements and cites supporting literature. Critically, each proposed evolutionary link is then validated for logical coherence and evidential support by a recovered natural language inference mechanism that interrogates the cited literature, ensuring that each step is grounded. We construct and validate 88 THE-Trees across diverse domains and release a benchmark dataset including up to 71k fact verifications covering 27k papers to foster further research. Experiments demonstrate that i) in graph completion, our THE-Tree improves hit@1 by 8% to 14% across multiple models compared to traditional citation networks; ii) for predicting future scientific developments, it improves hit@1 metric by nearly 10%; and iii) when combined with other methods, it boosts the performance of evaluating important scientific papers by almost 100%. By constructing explicit, verifiable pathways of scientific progression, THE-Tree provides a robust historical foundation for evaluating new hypotheses (human or AI-generated) and enables a computable science history, fostering evidence-based AI-driven scientific discovery.