Hugging Face Blog
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
Read the original on Hugging Face Blog →The Flow has not summarised this story yet — read it at Hugging Face Blog.
Related stories
arXiv AI
2d ago
Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Rubric Curriculum RL (RcRL) is a reinforcement learning approach that leverages the generation‑verification gap in non‑verifiable domains by using pairwise preferences over rollouts and a curriculum over rubric criteria. Unlike traditional methods that rely on absolute scoring and stationary judges, RcRL provides a more discriminative, non‑stationary signal, allowing policies to maintain output entropy and continue improving beyond 1,000 training steps. In experiments on creative writing and HealthBench, RcRL outperforms baseline models, achieving a 70.5% human win rate and significant accuracy gains over the base model.
arXiv Computation and Language
Oct 9
SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
SERL‑SQL introduces a selective execution‑grounded reinforcement learning framework for multi‑turn Text‑to‑SQL agents. It samples on‑policy interaction trajectories and employs a training‑only teacher to re‑score student actions using execution feedback, converting the teacher‑student likelihood gap into bounded, masked weights that reweight GRPO advantages only on SQL and tool‑action tokens. Experiments on BIRD, Spider, and cross‑domain benchmarks show competitive performance, achieving 76.56% execution accuracy on BIRD‑Dev and 89.92% on Spider‑Test, and the reward‑based selection strategy approaches the oracle Best‑of‑N upper bound.
arXiv AI
Oct 12
MENTOR: Learning from Failure with On-Policy Pedagogical Intervention
The paper introduces MENTOR, a multi‑agent framework that provides on‑policy pedagogical intervention to address zero‑reward collapse in reinforcement learning from verifiable rewards. MENTOR diagnoses failures in real time and generates targeted prompts to guide the learning agent, integrating seamlessly with existing policy optimization pipelines such as GRPO. Experiments on math and code generation tasks show that MENTOR significantly reduces collapse, achieving up to 78.3% relative gains on Llama‑3.2‑3B‑Instruct.
OpenAI Blog
Aug 3, 2017
Gathering human feedback
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
arXiv AI
Jun 24
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
arXiv:2606. 24839v1 Announce Type: new Abstract: Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics.
arXiv Computation and Language
Oct 9
HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments
HarnessSQL introduces a harness‑native post‑training framework that keeps the full stateful, multi‑turn interaction structure of real‑world database agents during both supervised fine‑tuning and reinforcement learning. By building isolated executable database environments with hidden execution oracles and retaining only verified trajectories for full‑sequence SFT, the method enables execution‑reward RL that aligns training with inference. Experiments on Spider 2.0‑SQLite show dramatic gains in execution accuracy for compact models, and the approach transfers effectively to out‑of‑distribution interactive benchmarks such as BIRD‑Interact and LiveSQLBench.