arXiv Machine Learning
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
4d ago
DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents
arXiv:2606.17029v2 Announce Type: replace Abstract: Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewa...
Hugging Face Trending Papers
Sep 28
Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents
Dr.Credit introduces a rubric‑grounded credit assignment method that evaluates intermediate tool turns in deep research agents by comparing the information returned to the history of accepted support for each rubric. Unlike traditional approaches that rely on ground‑truth answers, Dr.Credit uses task requirements as a shared reference, distinguishing new support from previously seen evidence and recognizing partial rubric fulfillment. Experiments on four benchmarks show that Dr.Credit outperforms open deep research baselines across all primary metrics, achieving performance competitive with proprietary models while enabling more efficient evidence acquisition and higher‑quality reports under limited turn budgets.
arXiv AI
Jul 23
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv AI
Jul 24
AREX: Towards a Recursively Self-Improving Agent for Deep Research
arXiv:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.
arXiv AI
Oct 5
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents
The paper introduces MIRA, a hierarchical architecture that separates meta-reasoning from execution for long-horizon research agents. An outer-loop meta-reasoner selects the next investigation based on a persistent research record, while an inner-loop executor carries out the chosen work order. The authors demonstrate that MIRA improves inference and compute allocation in theorem proving and neural-architecture research, and that a generative actor-critic variant (MIRA-AC) can be trained efficiently without directly optimizing long execution traces.
arXiv AI
Aug 25
DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning
DeepRefine is a reinforcement learning framework that improves the quality of pre‑constructed structured knowledge bases—such as knowledge graphs or LLM‑Wikis—by engaging in multi‑turn interactions with the base. It performs abductive diagnosis to locate defects, then applies targeted refinement actions to incrementally update the knowledge base. The system uses a Gain‑Beyond‑Draft reward to train its refinement policy end‑to‑end, achieving consistent downstream performance gains over strong baselines.