Hugging Face Trending Papers August 3, 2026

FLARE: Few-shot Learning-based Adaptive Reflective Engine

Read the original on Hugging Face Trending Papers →

Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Aug 25

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

arXiv:2608.23493v1 Announce Type: new Abstract: Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However,...

By Jialong Liu, Yuling Shi, Ning Yang, Xiaodong Gu, Zuchao Li

llms agents fine-tuning benchmarks

Hugging Face Trending Papers

Sep 1

CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures embedding small language models (SLMs) to perform reasoning over real-time telemetry. The state-of-th...

llms rag reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Sep 2

CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

The paper introduces CRAFT, a data‑centric fine‑tuning approach that aligns small language models (SLMs) for pre‑hoc reasoning in AI‑native 6G radio access networks (RAN). By automatically generating verified (input, trace, label) triplets and fine‑tuning with low‑rank adaptation, CRAFT achieves high accuracy and F1 scores on TRACTOR and IC xApp datasets while avoiding parse failures that plague RL methods like GRPO. It also reduces energy consumption by 59% compared to GRPO baselines, offering a more sustainable path to auditable AI in 6G RAN.

By Pranshav Gajjar, Vijay K Shah

llms rag reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 3

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

arXiv:2605. 28556v2 Announce Type: replace Abstract: As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated.

By Tomer Keren, Nitay Calderon, Asaf Yehudai, Yotam Perlitz, Michal Shmueli-Scheuer, Roi Reichart

llms agents benchmarks

arXiv AI

Jun 26

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.

By Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong

llms reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jul 28

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

arXiv:2602. 05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks.

By Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer, Sangwoong Yoon, Zhiyong Wang, Haitham Bou Ammar, Aurelien Lucchi, Ilija Bogunovic

llms reinforcement-learning

One email a morning, machine-written

Related stories

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks