Provides a diagnostic benchmark of 4,084 multiple-choice questions derived from longitudinal wearable time series, blood biomarkers, and demographics of 200 users to evaluate LLM reasoning on real-world wearable data. Uses 16 question types across complementary axes and a dual-grounding framework combining literature findings with population statistics.
Evaluates layer dropout (stochastic depth) in LLM pretraining, finds optimal layer distributions and time schedules that save ~20–25% training FLOPs at comparable or lower validation loss, and enables zero-shot layer skipping and self-speculative decoding for up to ~1.4–1.5× inference speedup.
Investigates long-horizon memorization in language models by evaluating how complementary continual-learning mechanisms (data, function, weight anchors and low-rank allocation/LoRA) compose to reduce catastrophic forgetting across 100 sequential tasks; best composition raises final retention from 1.2% to 34.9%.
Evaluates a weak teacher's RL-induced policy shift on the student's own rollouts and amplifies verifier-supported updates so stronger models can learn from weaker supervisors and surpass them. It rescales only verifier-supported policy-gradient components to preserve optimization fixed points while accelerating learning, reducing student updates versus standard RL or distillation.
AI Agent Papers2026
Explores a practical mechanism for recursive self-improvement by post-training LLMs: uses a routing harness to record agent executions and convert traces into curriculum-guided supervised fine-tuning and on-policy distillation data, closing an evaluation-selection-update loop and improving benchmark performance.
Adds a Next Concept Prediction objective that predicts discrete, product-quantized latent concepts spanning multiple tokens alongside next-token prediction, yielding faster pretraining convergence and measurable downstream gains with an 8.9B-parameter latent-space LLM.
AI Agent Papers2026
Defines recursive self-improvement (RSI) with an evaluation metric (Headroom-Closed Index) and a five-level autonomy roadmap—from executing human-specified improvements to recursively improving improvement mechanisms—while analyzing scenarios, verification challenges, and governance risks.
Haojun Zhang, Yi Zou +8Affiliation: Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang‡, Affiliation: XPeng Inc.
Progressively prunes and distills audio encoders for speech LLMs to cut inference cost while preserving decoder-facing embeddings, using behavioral probes, representation alignment, cross-scale distillation and LoRA finetuning; reports reduced macro-error on Chinese–English benchmarks.
AI Model2026
Preview agentic language model for research and engineering workflows that turns research questions into executable, verifiable workflows via tool use and long-context reasoning; built on a 744B-parameter MoE (GLM-5.2) with MIT-licensed BF16 and FP8 checkpoints.
Presents an open 7B dense foundation model for mathematical reasoning and tool-assisted web search, supporting 256K-token context. Key features: hybrid gated sliding-window + global attention for efficient long-context training, FP8 Muon optimizer, progressive 16K→64K→256K curriculum, and open-source weights, data, and recipes.
AI Agent Papers2026
Presents Atria Dawn Preview, an agentic foundation LLM trained with a Verifiable Experience Pipeline to connect tool-mediated interactions to executable environments; evaluated across 16 real-world research and engineering benchmarks with top scores on five, and a human–AI collaboration analysis of 769 task records.
AI Agent Papers2026
Estimates a model's probability of correctness by leveraging its past graded episodes: XConf recalls similar past cases and prompts the model to reflect and restate confidence, improving calibration and discrimination across reasoning, coding, multimodal QA, and agent tasks at much lower generation cost.