Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We present DIASENTINEL, a fully on-premise multi-agent system for one-year type 2 diabetes mellitus (T2DM) risk screening and guideline-grounded report generation from electronic health records (EHRs). The system integrates calibrated risk prediction, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer combining rule-based checks with LLM entailment. The demonstration provides a real-time batch-screening dashboard and an interactive patient report interface with cited recommendations, verification results, and raw EHR comparison. DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support.
Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks paired with a critic. Rubrics extracted from scientific papers can supply the critic. Existing pipelines, however, draw the question and the criteria from the same content, so the reward can be earned by paraphrase. The rubric is further compressed into a single scalar per rollout. We introduce PaperGym, a unified framework that turns each research paper into a complete training environment. PaperGym exploits the structure of a paper: the question is synthesized from the research goal and background, while the criteria are derived from the method and experiments. The criteria span methodological innovation and experimental design, and criterion leakage falls to 3.7%, versus 11.90% to 34.10% in existing datasets. Training uses the rubric twice: first as privileged context for OPSD's self-teacher, then as the reward for GRPO. Across Qwen3-1.7B/4B/8B, this schedule outperforms supervised fine-tuning, either stage alone, and the reverse ordering, improving five-benchmark averages by +5.6, +5.0, and +4.8 points. With the recipe held fixed, models trained on PaperGym-20k win 58.1% of three-way comparisons, against 28.2% for RubricHub Science. The trained Qwen3-8B reaches 73.48 on ResearchQA, above the far larger Kimi K2.6. We release the pipeline, the 20,000-instance corpus PaperGym-20k, and the benchmarks PaperGym-Innov and PaperGym-Design.
Yuhan Wang, Zhengxi Lu, Yuchen Yan et al.· 0 citations
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi et al.· 0 citations
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them as fixed policies. It therefore remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions. We introduce \textbf{S\textsuperscript{3}Gym}, an interactive benchmark for evaluating LLM self-improvement through three coupled capabilities: \textbf{Self-Testing}, \textbf{Self-Judging}, and \textbf{Self-Improvement}. S$^3$Gym separates permissive exploration from strict held-out evaluation and instantiates this protocol in seven text-based games with executable environment verifiers. We evaluate three pathways for incorporating interaction experience: direct History ICL, score-conditioned Summary Memory, and parameter Training.
Our experiments reveal that self-improvement is neither automatic nor uniform. Context-level experience improves performance for several model--game pairs, but the most effective pathway depends strongly on the task structure: summaries are beneficial when experience can be compressed into reusable strategic rules, yet often underperform raw history when success depends on precise, state-contingent information. Parameter training produces substantial gains on some tasks, but also exhibits unstable improvement and severe negative transfer on others. These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies. S$^3$Gym provides a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable self-improvement.
Jiajun Shi, Siyuan Tao, Yuhao Wu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The Jacobian Lens (J-lens) is a recent tool for interpreting LLMs. It reads a hidden state as a ranked list of vocabulary tokens, leaving multi-token concepts without a representation of their own. The original J-lens work addresses this limitation with Template Lens, which precomputes vectors for a fixed phrase vocabulary, and Oracle Lens, which fine-tunes components to propose phrases and reconstruct phrase vectors. We ask whether multi-token concepts and their vectors can instead be recovered directly from J-lens and the frozen model. We find that the first token of a multi-token concept is about as readable as a single-token concept. Given the correct first token and source prompt, the frozen model recovers the second token in 88.3% of two-token cases. We show that a vector for the complete concept can be recovered from subsequent hidden states in a single forward pass. We therefore use J-lens to propose first tokens and let the frozen model complete candidate concepts. We then recover a vector for each candidate and score it alongside the complete vocabulary. Across 496 multi-hop clozes on Gemma-3-12B-IT, Llama-3.1-8B, and Qwen3-14B, our method achieves an average $\mathrm{Rank@}10$ of 43.1%, compared with 27.6% for Template Lens. Without the J-lens clue, performance drops to 21.6%, showing that the first-token clue substantially improves readout. Causal concept swaps using the recovered vectors achieve an average $\mathrm{succ}@10$ of 61.4%, compared with 26.2% for Template Lens under the same intervention. These results show that first-token clues can guide multi-token concept recovery, while subsequent hidden states provide vectors for readout and intervention.
Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning full reasoning chains into shorter traces for model adaptation, making token selection the central challenge. Existing methods often rely on external scorers or heuristic signals only indirectly tied to the model's internal answer computation. We instead adopt a model-internal perspective: as the model forms an answer, each reasoning token leaves a ripple in the residual stream, the model's \emph{stream of thought}, and the magnitude of this ripple reflects the token's contribution to the answer computation. Building on this view, we propose \textsc{MIST} (Model-Internal Saliency for Token-level CoT compression), which defines token importance along two complementary axes: \emph{necessity}, the drop in answer likelihood when a token's internal contribution is removed, and \emph{sufficiency}, the gain in answer likelihood when that contribution alone is provided. Combining the two yields a unified importance score for pruning. Across four reasoning benchmarks and four models, \textsc{MIST} consistently outperforms baseline methods, suggesting that model-internal saliency provides an effective proxy for reasoning-token importance.
Tianyi Zhao, Yinhan He, Wendy Zheng et al.· 0 citations
When information extraction fails, a natural instinct is to improve the model doing it: for example, by scaling it up or refining its reasoning. In this paper, we show that another part of the pipeline matters at least as much: the queries used to elicit this information. Across four clinical benchmarks and five LLMs, improving the question design alone raises performance by 18.6 F1-score points, i.e. more than using larger extraction models. To make such question design learnable, we introduce List of Questions (LoQ), which generates document-specific question sets, and FeedQ, a feedback-driven optimization method that iteratively refines questions against extraction outcomes. The resulting optimized questions can be used to train lightweight generators: with fine-tuning, 4B-parameter models match or outperform expert-derived baselines and substantially exceed the performance of much larger untuned models. We release a dataset of 12,820 optimized questions to support a broader shift in information extraction research toward treating question design as a first-class problem.
Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity types within unstructured text. Faced with the continuous influx of entity types, INER grapples with two significant challenges: the widespread issue of catastrophic forgetting and the unique shift issue of the non-entity type semantics. While pseudo-labeling-based INER methods have proven effective in addressing these challenges, a previously overlooked issue arises: the biased context problem. Our analysis shows that, in new sentences, the contextual associations of tokens representing old entity types exhibit a significantly stronger bias towards new entity types compared to their contexts in old sentences. This tendency intensifies the degradation of old knowledge while promoting the overfitting of new knowledge. To solve this biased context, we propose a Type-Balanced Contextual Learning (TBCL) method, featuring a sentence-duplet learning scheme and a contextual consistency loss. This approach offers a fresh perspective for INER through context analysis. Extensive experiments across ten INER settings on three highly recognized datasets showcase the efficacy of our TBCL method, highlighting its proficiency in resolving the biased context issue inherent in pseudo-labeling based INER approaches.
Duzhen Zhang, Yahan Yu, Xiuyi Chen et al.· 0 citations
Neural audio codecs (NACs) convert speech into discrete token sequences, and prior work has reported that these sequences follow language-like statistical laws. This paper analyzes the token statistics of 13 NACs spanning multi-codebook residual vector quantization (RVQ), single-codebook VQ, and non-VQ designs, evaluated on three corpora under clean, white-noise, and real-world DEMAND-noise conditions. Zipf and Heaps parameters, unigram entropy, codebook occupancy, and Jensen-Shannon divergence (JSD) are estimated from matched token samples with explicit fit-validity safeguards and family-conditional $n$-gram orders. Corpus identity explains little variance in any metric, whereas acoustic condition and quantizer meta-category dominate in a metric-dependent way, and unigram entropy is the metric most strongly associated with meta-category. Clean-to-noise JSD computed at a common unigram order is associated with mel-cepstral distortion most clearly under DEMAND noise. The collapse and explosion degradation signatures previously reported for RVQ codecs concentrate in RVQ cells under white and DEMAND noise, respectively; explosion also occurs in non-VQ codecs, and single-codebook VQ codecs shift in occupancy and distribution shape without either signature. These results provide architecture-conditioned conventions for applying language-statistical analysis to NAC tokens.
Joonyong Park, Shinnosuke Takamichi, David M. Chan et al.· 0 citations
Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as reinforcement learning rewards without losing alignment with human listeners. We study this question with Group Relative Policy Optimization (GRPO) using learned rewards for anime-like speaking style, naturalness, likability, and arousal. To prevent perceptual rewards from being optimized through transcript drift, we introduce a character error rate (CER) zone constraint and compare policy optimization with Best-of-$N$ reranking under the same reward gate. Across single-reward runs, each reward primarily improves its own target metric, showing that subjective predictors are not interchangeable quality surrogates. Multi-rater A/B tests further show uneven human transfer, while a reward-gap analysis separates average transfer from within-axis calibration: signed reward gaps significantly predict listener choices in the pooled analysis, whereas residual CER gaps do not, but per-axis calibration remains heterogeneous. Best-of-8 is a strong human-level baseline and is not clearly worse than GRPO perceptually, suggesting that GRPO should be viewed as amortizing reward-selected behavior into the policy rather than uniformly outperforming reranking. These results support analyzing subjective speech rewards as predictor-axis-base tuples and provide practical diagnostics for selecting rewards before multi-reward speech post-training.
Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 142 consultations: 565 notes from recorded UK primary-care and US ambulatory encounters plus authored scenarios. Twelve discovery passes proposed 13,678 candidate errors; the 5,898 clearing an importance filter went to an adversarial panel of two models from different families, each told to refute what it could, and 618 survived. One note in three (31.3% [27.0, 35.6]) carries a verified failure, concentrated in allergy and medication information, invented patient identity, and history written up as examination on telephone consultations that can contain none. No product was given a patient record; setting aside the two classes a record would have prefilled, invented identity and dates, the rate is 24.8% [20.8, 29.0]. One failure mode did not fit our scheme, drawn from published scribe-error taxonomies: a treatment the clinician retracts, recorded as delivered care. Two clinicians adjudicated blind, disjoint samples: a physician author upheld 20 of 21 findings (95.2% [77.3, 99.2]) and an independent clinician, not an author, 12 of 12 ([75.8, 100]); both judged every sampled refusal genuine. A failure rate depends on the instrument as much as the scribes. With model, evidence and settings fixed, the review instruction alone moves the share of candidates verified from 9.3% to 79.0%, and the reviewing family moves it too: alone at that instruction the gentler flags 54.8% of notes against 27.8%. Between 28% and 97% of sampled notes carry a failure depending on the standard. Published audits disagree among themselves by a margin instrument differences alone can produce: omission is 54-86% of their errors against our 23.1%. We release all 618 findings with transcript-side evidence, every prompt and model version, and the re-runnable pipeline.
Sebastian Fox, Luke Markham, Ryan Lail et al.· 0 citations
Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.
Sebastian Fox, Luke Markham, Ryan Lail et al.· 0 citations
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
