Daily Archive
Updated from current HFEPX corpus (Feb 27, 2026). 7 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. Common annotation unit: Trajectory. Frequently cited benchmark: MATH. Common metric signal: agreement. Newest paper in this set is from Feb 2, 2026.
Updated from current HFEPX corpus (Feb 27, 2026). This page covers 7 papers centered on HFEPX Daily Archive: 2026-02-02. Common evaluation modes include Automatic Metrics, Simulation Env, with benchmark emphasis on MATH, Retrieval. Use the anchored takeaways below to compare protocol choices and identify papers with stronger evidence depth.
Evaluation emphasis: Automatic Metrics and Simulation Env appear frequently in this slice.
Evidence: Proof-RM: A Scalable and Generalizable Reward Model for Math Proof , DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations , Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
Benchmark concentration: MATH, Retrieval helps control cross-paper variance.
Evidence: DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations , Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts , CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
Metric concentration: agreement, accuracy is repeatedly reported in this group.
Evidence: Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts , CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models , Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
Stratify by benchmark (MATH vs Retrieval) before comparing methods.
Evidence: CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models , Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation , Mechanistic Indicators of Steering Effectiveness in Large Language Models
Track metric sensitivity by reporting both agreement and accuracy.
Evidence: Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation , Mechanistic Indicators of Steering Effectiveness in Large Language Models , Argument Rarity-based Originality Assessment for AI-Assisted Writing
Papers with explicit human feedback is visible in approximately 0% of papers in this set.
Evidence: Mechanistic Indicators of Steering Effectiveness in Large Language Models , Argument Rarity-based Originality Assessment for AI-Assisted Writing , Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
Papers with explicit human feedback
Coverage is a replication risk (0% vs 45% target).
Papers reporting quality controls
Coverage is a replication risk (0% vs 30% target).
Papers naming benchmarks/datasets
Coverage is usable but incomplete (28.6% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (71.4% vs 35% target).
Papers with known rater population
Coverage is a replication risk (0% vs 35% target).
Papers with known annotation unit
Coverage is a replication risk (14.3% vs 35% target).
1. Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
Start with this anchor paper for scope and protocol framing. Covers Automatic Metrics.
2. DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations
Covers Simulation Env.
Covers Automatic Metrics.
4. CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
Covers Automatic Metrics.
5. Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
Covers Automatic Metrics.
6. Mechanistic Indicators of Steering Effectiveness in Large Language Models
Covers Automatic Metrics.
7. Argument Rarity-based Originality Assessment for AI-Assisted Writing
Covers Automatic Metrics.
automatic_metrics vs simulation_env
both=0, left_only=6, right_only=1
0 papers use both Automatic Metrics and Simulation Env.
Haotong Yang, Zitong Wang, Shijia Kang, Siqi Yang, Wenkai Yu · Feb 2, 2026
In this work, we design a *scalable* data-construction pipeline that, with minimal human effort, leverages LLMs to generate a large quantity of high-quality ``**question-proof-check**'' triplet data.
Minghao Li, Ruihang Wang, Rui Tan, Yonggang Wen · Feb 2, 2026
However, manually designing piecewise deep reinforcement learning (DRL) agents cannot keep pace with frequent dynamics shifts and service-level agreement (SLA) changes of an evolving DC.
Wenhao Li, Daohai Yu, Gen Luo, Yuxin Zhang, Fei Chao · Feb 2, 2026
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time.
Weining Fu, Kai Shu, Kui Xu, Qiangfeng Cliff Zhang · Feb 2, 2026
Cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling near-atomic-level visualization of biomolecular assemblies.
Zhanghao Hu, Qinglin Zhu, Hanqi Yan, Yulan He, Lin Gui · Feb 2, 2026
Agent memory systems often adopt the standard Retrieval-Augmented Generation (RAG) pipeline, yet its underlying assumptions differ in this setting.
Mehdi Jafari, Hao Xue, Flora Salim · Feb 2, 2026
Despite its widespread use, the mechanistic factors that govern when steering succeeds or fails remain poorly understood, as prior work has relied primarily on black-box outputs or LLM-based judges.
Keito Inoshita, Michiaki Omura, Tsukasa Yamanaka, Go Maeda, Kentaro Tsuji · Feb 2, 2026
Experiments using 1,375 human essays and 1,000 AI-generated essays on two argumentative topics revealed three key findings.
