DeepPlanner is an end-to-end reinforcement learning framework designed to enhance the planning capabilities of deep research agents. It introduces an entropy-based advantage shaping mechanism that allocates larger updates to high-entropy planning tokens and selectively upweights sample-level advantages during planning-intensive rollouts. Experiments on seven deep research benchmarks show that DeepPlanner improves planning quality and achieves state‑of‑the‑art results with a lower training budget.
arXiv:2610.15910v2 Announce Type: replace Abstract: Deep Research agents rely on long-horizon reasoning and iterative tool use to solve complex information-seeking tasks. However, adaptive decision-m...
arXiv:2605.24218v2 Announce Type: replace Abstract: Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how...
The paper introduces Multi-Level Reasoning (MLR), a two-level stochastic framework that separates long chain-of-thought generation into a high-level planner producing structured step descriptors and a low-level executor generating detailed reasoning. MLR replaces single-policy reinforcement learning with an iterative Step‑DPO preference optimization that uses Twisted Sequential Monte Carlo for scalable, stepwise supervision, improving training stability and accuracy. Experiments on math, science, and logic benchmarks show that MLR outperforms both supervised fine‑tuning and strong RL baselines while maintaining robustness over extended reasoning horizons.
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: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.
APEx is a hierarchical framework that organizes a deep research agent’s interaction history into instance-level trajectory memories and category-level procedural skills. It couples these through an Executor, Distiller, and Planner, trained with a three-stage alternating GRPO paradigm to enable reward-guided skill distillation. At test time, distilled skills act as procedural priors for online Planner adaptation via skill-guided reinforcement learning, achieving state‑of‑the‑art results on seven benchmarks, outperforming GPT‑5.4 by 14.7 points and the best memory‑augmented baseline by 3.0 points.
The paper introduces Rollout-Time Intervention (RTI), a method that uses reward-side evidence during rollouts to transform unsuccessful trajectories into successful ones, thereby providing learning signals for tasks beyond a policy’s intrinsic exploration limits. RTI filters out trajectories with excessive distributional shifts, allowing these off-policy interventions to guide policy optimization effectively. Experiments on five benchmarks show that RTI consistently outperforms existing RL baselines, enabling post-trained policies to approach the performance of stronger large language models and surpass their original capability boundaries.
PlanPO introduces a group planning-aware policy optimization method for multi-turn agentic large language models, addressing the issue of advantage collapse caused by treating all successful trajectories equally. By incorporating coarse-to-fine advantage signals that reflect differences in trajectory and turn lengths, PlanPO encourages agents to learn generalizable planning and generation behaviors. Experiments show a 27.2% average improvement over GRPO on benchmarks such as ALFWorld, WebShop, and SciWorld, with minimal extra training cost.
RubricEM is a unified reinforcement learning framework designed for deep research agents that plan, search, evaluate evidence, and synthesize long‑form reports. It introduces rubric‑guided policy decomposition, combining supervised fine‑tuning to scaffold agents with rubrics, stage‑structured GRPO for fine‑grained credit assignment, and a reflection meta‑policy for experience reuse. The resulting RubricEM‑8B model outperforms larger open models on four long‑form research benchmarks and approaches the performance of proprietary deep‑research systems.
arXiv:2606. 13710v1 Announce Type: new Abstract: Deep research and agent evolution serve as de-facto tasks for AI agents in real-world applications toward artificial general intelligence.
Guided-RLVR introduces a lightweight controller to reinforcement learning with verifiable rewards (RLVR), injecting semantically meaningful steering tokens into the sampling distribution. This strategy encourages large language models to explore multiple reasoning perspectives, expanding the set of reasoning trajectories. Experiments on mathematical reasoning and code generation benchmarks demonstrate that Guided-RLVR consistently outperforms existing RLVR methods while producing more diverse reasoning paths.
IDRBench is a benchmark designed to evaluate the interactive capabilities of deep research agents that use large language models. It introduces controlled opportunities for clarification within a common workflow, comparing autonomous and interactive trajectories by measuring task‑specific report alignment and interaction cost. Experiments on 100 tasks with seven LLMs show that interaction consistently improves alignment, though its effectiveness varies depending on the agents’ questions and feedback integration.