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...
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: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:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.
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.
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.
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...
ContextPilot is a proactive context‑management framework designed to improve long‑horizon agentic reasoning with large language models. It expands the toolset to include planning, long‑term memory, and soft context offloading, and introduces a reinforcement‑learning strategy that focuses on critical editing decisions and assigns action‑level advantages. Experiments on long‑context QA and deep search tasks demonstrate that ContextPilot achieves stronger performance with a more compact working context, outperforming existing baselines across various base models and benchmarks.
arXiv:2606. 15367v1 Announce Type: new Abstract: Deep research agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering, reasoning, and report generation.
arXiv:2610.02824v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requireme...
arXiv:2608. 16156v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult.
arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assign...