Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

Scientific hypothesis generation requires tracking how knowledge evolves, not just what is currently known. We introduce Continuous Knowledge Metabolism (CKM), a framework that processes scientific literature through sliding time windows and incrementally updates a structured knowledge base as new findings arrive. We present CKM-Lite, an efficient variant that achieves strong predictive coverage through incremental accumulation, outperforming batch processing on hit rate (+2.8%, p=0.006), hypothesis yield (+3.6, p<0.001), and best-match alignment (+0.43, p<0.001) while reducing token cost by 92%. To understand what drives these differences, we develop CKM-Full, an instrumented variant that categorizes each new finding as novel, confirming, or contradicting, detects knowledge change signals, and conditions hypothesis generation on the full evolution trajectory. Analyzing 892 hypotheses generated by CKM-Full across 50 research topics, alongside parallel runs of the other variants, we report four empirical observations: (1) incremental processing outperforms batch baseline across predictive and efficiency metrics; (2) change-aware instrumentation is associated with higher LLM-judged novelty (Cohen's d=3.46) but lower predictive coverage, revealing a quality-coverage trade-off; (3) a field's trajectory stability is associated with hypothesis success (r=-0.28, p=0.051), suggesting boundary conditions for literature-based prediction; (4) knowledge convergence signals are associated with nearly 5x higher hit rate than contradiction signals, pointing to differential predictability across change types. These findings suggest that the character of generated hypotheses is shaped not only by how much literature is processed, but also by how it is processed. They further indicate that evaluation frameworks must account for the quality-coverage trade-off rather than optimize for a single metric.

ClawBench: Can AI Agents Complete Everyday Online Tasks?

AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework of 153 simple tasks that people need to accomplish regularly in their lives and work, spanning 144 live platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require demanding capabilities beyond existing benchmarks, such as obtaining relevant information from user-provided documents, navigating multi-step workflows across diverse platforms, and write-heavy operations like filling in many detailed forms correctly. Unlike existing benchmarks that evaluate agents in offline sandboxes with static pages, ClawBench operates on production websites, preserving the full complexity, dynamic nature, and challenges of real-world web interaction. A lightweight interception layer captures and blocks only the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 7 frontier models show that both proprietary and open-source models can complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%. Progress on ClawBench brings us closer to AI agents that can function as reliable general-purpose assistants.

OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning

Recent large multimodal models (LMMs) have made rapid progress in visual grounding, document understanding, and diagram reasoning tasks. However, their ability to convert Printed Circuit Board (PCB) schematic diagrams into machine-readable spatially weighted netlist graphs, jointly capturing component attributes, connectivity, and geometry, remains largely underexplored, despite such graph representations are the backbone of practical electronic design automation (EDA) workflows. To bridge this gap, we introduce OmniSch, the first comprehensive benchmark designed to assess LMMs on schematic understanding and spatial netlist graph construction. OmniSch contains 1,854 real-world schematic diagrams and includes four tasks: (1) visual grounding for schematic entities, with 109.9K grounded instances aligning 423.4K diagram semantic labels to their visual regions; (2) diagram-to-graph reasoning, understanding topological relationship among diagram elements; (3) geometric reasoning, constructing layout-dependent weights for each connection; and (4) tool-augmented agentic reasoning for visual search, invoking external tools to accomplish (1)-(3). Our results reveal substantial gaps of current LMMs in interpreting schematic engineering artifacts, including unreliable fine-grained grounding, brittle layout-to-graph parsing, inconsistent global connectivity reasoning and inefficient visual exploration.

ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent to human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process. This allows an Orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing. Central to this framework is a Dual-Memory architecture: a mutable Working Memory that maintains the evolving patient state for context-aware reasoning, and a static Experience Memory that retrieves clinical guidelines and historical cases via an active feedback loop. Extensive experiments demonstrate that ClinicalAgents achieves state-of-the-art performance, significantly enhancing both diagnostic accuracy and explainability compared to strong single-agent and multi-agent baselines.

Attention-based Pin Site Image Classification in Orthopaedic Patients with External Fixators

Pin sites represent the interface where a metal pin or wire from the external environment passes through the skin into the internal environment of the limb. These pins or wires connect an external fixator to the bone to stabilize the bone segments in a patient with trauma or deformity. Because these pin sites represent an opportunity for external skin flora to enter the internal environment of the limb, infections of the pin site are common. These pin site infections are painful, annoying, and cause increased morbidity to the patients. Improving the identification and management of pin site infections would greatly enhance the patient experience when external fixators are used. For this, this paper collects and produces a dataset on pin sites wound infections and proposes a deep learning (DL) method to classify pin sites images based on their appearance: Group A displayed signs of inflammation or infection, while Group B showed no evident complications. Unlike studies that primarily focus on open wounds, our research includes potential interventions at the metal pin/skin interface. Our attention-based deep learning model addresses this complexity by emphasizing relevant regions and minimizing distractions from the pins. Moreover, we introduce an Efficient Redundant Reconstruction Convolution (ERRC) method to enhance the richness of feature maps while reducing the number of parameters. Our model outperforms baseline methods with an AUC of 0.975 and an F1-score of 0.927, requiring only 5.77 M parameters. These results highlight the potential of DL in differentiating pin sites only based on visual signs of infection, aligning with healthcare professional assessments, while further validation with more data remains essential.

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However, its adoption has been limited by the lack of high-quality draft models and scalable training infrastructure. We introduce SpecForge, an open-source, production-oriented framework for training speculative decoding models with full support for EAGLE-3. SpecForge incorporates target-draft decoupling, hybrid parallelism, optimized training kernels, and integration with production-grade inference engines, enabling up to 9.9x faster EAGLE-3 training for Qwen3-235B-A22B. In addition, we release SpecBundle, a suite of production-grade EAGLE-3 draft models trained with SpecForge for mainstream open-source LLMs. Through a systematic study of speculative decoding training recipes, SpecBundle addresses the scarcity of high-quality drafts in the community, and our draft models achieve up to 4.48x end-to-end inference speedup on SGLang, establishing SpecForge as a practical foundation for real-world speculative decoding deployment.

When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking processes do not consistently yield performance gains and may even lead to degradation due to ``visual anchor drifting'', where models increasingly rely on self-generated text, sidelining visual inputs and causing hallucinations. While existing mitigations typically introduce specific mechanisms for the model to re-attend to visual inputs during inference, these approaches often incur prohibitive training costs and suffer from poor generalizability across different architectures. To address this, we propose FrameRepeat, an automated enhancement framework which features a lightweight repeat scoring module that enables Video-LLMs to autonomously identify which frames should be reinforced. We introduce a novel training strategy, Add-One-In (AOI), that uses MLLM output probabilities to generate supervision signals representing repeat gain. This can be used to train a frame scoring network, which guides the frame repetition behavior. Experimental results across multiple models and datasets demonstrate that FrameRepeat is both effective and generalizable in strengthening important visual cues during the reasoning process.

Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System

Approximate nearest neighbor (ANN) search is widely used in the retrieval stage of large-scale recommendation systems. In this stage, candidate items are indexed using their learned embedding vectors, and ANN search is executed for each user (or item) query to retrieve a set of relevant items. However, ANN-based retrieval has two key limitations. First, item embeddings and their indices are typically learned in separate stages: indexing is often performed offline after embeddings are trained, which can yield suboptimal retrieval quality-especially for newly created items. Second, although ANN offers sublinear query time, it must still be run for every request, incurring substantial computation cost at industry scale. In this paper, we propose MultiFaceted Learnable Index (MFLI), a scalable, real-time retrieval paradigm that learns multifaceted item embeddings and indices within a unified framework and eliminates ANN search at serving time. Specifically, we construct a multifaceted hierarchical codebook via residual quantization of item embeddings and co-train the codebook with the embeddings. We further introduce an efficient multifaceted indexing structure and mechanisms that support real-time updates. At serving time, the learned hierarchical indices are used directly to identify relevant items, avoiding ANN search altogether. Extensive experiments on real-world data with billions of users show that MFLI improves recall on engagement tasks by up to 11.8\%, cold-content delivery by up to 57.29\%, and semantic relevance by 13.5\% compared with prior state-of-the-art methods. We also deploy MFLI in the system and report online experimental results demonstrating improved engagement, less popularity bias, and higher serving efficiency.

Semantic Search At LinkedIn

Semantic search with large language models (LLMs) enables retrieval by meaning rather than keyword overlap, but scaling it requires major inference efficiency advances. We present LinkedIn's LLM-based semantic search framework for AI Job Search and AI People Search, combining an LLM relevance judge, embedding-based retrieval, and a compact Small Language Model trained via multi-teacher distillation to jointly optimize relevance and engagement. A prefill-oriented inference architecture co-designed with model pruning, context compression, and text-embedding hybrid interactions boosts ranking throughput by over 75x under a fixed latency constraint while preserving near-teacher-level NDCG, enabling one of the first production LLM-based ranking systems with efficiency comparable to traditional approaches and delivering significant gains in quality and user engagement.

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled formulation introduces substantial deployment and adaptation lag: (1) high time-to-serve, since a speculator must be trained offline for a considerable period before deployment; (2) delayed utility feedback, since the true end-to-end decoding speedup is only known after training and cannot be inferred reliably from acceptance rate alone due to model-architecture and system-level overheads; and (3) domain-drift degradation, as the target model is repurposed to new domains and the speculator becomes stale and less effective. To address these issues, we present Aurora, a unified training-serving system that closes the loop by continuously learning a speculator directly from live inference traces. Aurora reframes online speculator learning as an asynchronous reinforcement-learning problem: accepted tokens provide positive feedback, while rejected speculator proposals provide implicit negative feedback that we exploit to improve sample efficiency. Our design integrates an SGLang-based inference server with an asynchronous training server, enabling hot-swapped speculator updates without service interruption. Crucially, Aurora supports day-0 deployment: a speculator can be served immediately and rapidly adapted to live traffic, improving system performance while providing immediate utility feedback. Across experiments, Aurora achieves a 1.5x day-0 speedup on recently released frontier models (e.g., MiniMax M2.1 229B and Qwen3-Coder-Next 80B). Aurora also adapts effectively to distribution shifts in user traffic, delivering an additional 1.25x speedup over a well-trained but static speculator on widely used models (e.g., Qwen3 and Llama3).