Human Feedback and Eval Paper Explorer

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We present IDP (Intelligent Document Processing) Accelerator, a framework enabling agentic AI for end-to-end document intelligence with four key components: (1) DocSplit, a novel benchmark dataset and multimodal classifier using BIO tagging…

Match reason: Keyword overlap 1/1 across title and protocol fields.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.
• Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues.
• We evaluate on both static and dynamic long-horizon interaction benchmarks.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We introduce Vibe Code Bench, a benchmark of 100 web application specifications (50 public validation, 50 held-out test) with 964 browser-based workflows comprising 10,131 substeps, evaluated against deployed applications by an autonomous…
• We identify self-testing during generation as a strong performance predictor (Pearson r=0.72), and show through a completed human alignment study that evaluator selection materially affects outcomes (31.8-93.6% pairwise step-level…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive…
• Extensive experiments across 4 benchmarks confirm the effectiveness of MM-Mem on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.
• Across math reasoning benchmarks, we find that step-level recombination is most beneficial on harder problems, and ablations highlight the importance of the final AR solver in converting stitched but imperfect rationales into accurate…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass of an MLLM.
• To rigorously evaluate this capability, we further present ZoomBench, a hybrid-annotated benchmark of 845 VQA data spanning six fine-grained perceptual dimensions, together with a dual-view protocol that quantifies the global--regional…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.
• While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence.
• Motivated by the recent insights that evaluation and debate mechanisms can improve problem-solving in multi-agent systems, we propose TopoDIM, a framework for one-shot Topology generation with Diverse Interaction Modes.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks.
• Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively,…