A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research.
Every paper includes structured metadata for quick triage.
Experiments on three multimodal MoE models across six benchmarks demonstrate consistent improvements, with gains of up to 3.17% on complex visual reasoning tasks.
Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.
We present a controlled empirical benchmark of seven recent reasoning-oriented instruction-tuned models spanning dense and MoE designs, namely Gemma-4-E2B, Gemma-4-E4B, Gemma-4-26B-A4B, Phi-4-mini-reasoning, Phi-4-reasoning, Qwen3-8B, and…
The study covers 8,400 total model-dataset-prompt evaluations and records accuracy, latency, peak GPU memory usage (VRAM), and an approximate floating-point operations (FLOPs)-per-token proxy.
Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.
Our evaluation demonstrates that SemLink achieves a Recall of 96.00%, comparable to state-of-the-art LLMs (GPT-5.2), while operating approximately 47.5 times faster and requiring significantly fewer computational resources.
Prior evaluations have largely focused on tasks that do not require extracting large amounts of information from the context.
Our analysis identifies two key reasons for poor accuracy: low-rank projection of keys and unreliable landmarks, and proposes a simpler alternative strategy that significantly improves accuracy across multiple LLM families and benchmarks.
Although recent LLM-based ASR models have shown promising performance on public benchmarks, it remains challenging to balance recognition quality with latency and overhead, while hallucinations further limit real-world deployment.
Experiments on Mandarin and English benchmarks show that our method achieves competitive performance with state-of-the-art models using only 2.3B parameters, while also effectively mitigating hallucinations through our decoupling-oriented…
Validation comprised technical benchmarking of each AI component, including comparative assessments of speech synthesis providers and multilingual translation models (NLLB 200 and EuroLLM 1.7B variants).
Technical evaluations confirmed the suitability of the platform for real time XR deployment.
Autonomous agents are moving beyond simple retrieval tasks to become economic actors that invoke APIs, sequence workflows, and make real-time decisions.
The primary contribution is a controlled agent-payment infrastructure and reference architecture that demonstrates how agentic access monetization can be adapted to fiat systems without discarding security and policy guarantees.
Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions.
We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size.
The advent of agentic multimodal models has empowered systems to actively interact with external environments.
Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.
Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive agent: depth, complexity, ambiguity, precision and real-time constraints.
We first propose DD-MM-PAS (Demand Detection, Memory Modeling, Proactive Agent System) as a general paradigm for streaming proactive AI agent.
We introduce a weak supervision framework that combines three complementary grounding signals: substring matching, sentence embedding similarity, and an LLM as a judge verdict to label generated responses as grounded or hallucinated without…
Transformer-based probes achieve the strongest discrimination, with M2 performing best on 5-fold average AUC/F1, and M3 performing best on both single-fold validation and held-out test evaluation.
We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.
Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains.
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…