Daily Archive
Updated from current HFEPX corpus (Feb 27, 2026). 5 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. Frequently cited benchmark: AIME. Common metric signal: cost. Newest paper in this set is from Feb 5, 2026.
Updated from current HFEPX corpus (Feb 27, 2026). This page covers 5 papers centered on HFEPX Daily Archive: 2026-02-05. Common evaluation modes include Automatic Metrics, Simulation Env, with benchmark emphasis on AIME, Airbench. 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: Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering , Transport and Merge: Cross-Architecture Merging for Large Language Models , Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
Benchmark concentration: AIME, Airbench helps control cross-paper variance.
Evidence: Transport and Merge: Cross-Architecture Merging for Large Language Models , Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions , The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems
Metric concentration: cost, mse is repeatedly reported in this group.
Evidence: Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions , The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems , EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
Stratify by benchmark (AIME vs Airbench) before comparing methods.
Evidence: The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems , EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization , Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering
Track metric sensitivity by reporting both cost and mse.
Evidence: EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization , Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering , Transport and Merge: Cross-Architecture Merging for Large Language Models
Papers with explicit human feedback is visible in approximately 0% of papers in this set.
Evidence: Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering , Transport and Merge: Cross-Architecture Merging for Large Language Models , Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
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 strong (40% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (40% 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 (0% vs 35% target).
1. Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering
Start with this anchor paper for scope and protocol framing. Covers Automatic Metrics.
2. Transport and Merge: Cross-Architecture Merging for Large Language Models
Covers Automatic Metrics.
3. Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
Covers Automatic Metrics.
4. The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems
Covers Simulation Env.
5. EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
Covers Automatic Metrics.
automatic_metrics vs simulation_env
both=0, left_only=4, right_only=1
0 papers use both Automatic Metrics and Simulation Env.
Amir H. Ashouri, Shayan Shirahmad Gale Bagi, Kavin Satheeskumar, Tejas Srikanth, Jonathan Zhao · Feb 5, 2026
Traditionally, such locally optimized decisions are made by hand-coded algorithms tuned for a small number of benchmarks, often requiring significant effort to be retuned when the benchmark suite changes.
Chenhang Cui, Binyun Yang, Fei Shen, Yuxin Chen, Jingnan Zheng · Feb 5, 2026
Large language models (LLMs) achieve strong capabilities by scaling model capacity and training data, yet many real-world deployments rely on smaller models trained or adapted from low-resource data.
Jinchuan Tian, Haoran Wang, Bo-Hao Su, Chien-yu Huang, Qingzheng Wang · Feb 5, 2026
In contrast, human intelligence processes audio holistically, seamlessly bridging physical signals with abstract cognitive concepts to execute complex tasks.
Shangbin Feng, Kishan Panaganti, Yulia Tsvetkov, Wenhao Yu · Feb 5, 2026
Model collaboration -- systems where multiple language models (LMs) collaborate -- combines the strengths of diverse models with cost in loading multiple LMs.
Kevin Han, Yuhang Zhou, Mingze Gao, Gedi Zhou, Serena Li · Feb 5, 2026
Empirically, EBPO consistently outperforms GRPO and other established baselines across diverse benchmarks, including AIME and OlympiadBench.
