The paper introduces AnySearch, a reinforcement‑learning framework that trains a single policy to perform budget‑aware search for large language models under any budget constraint. The training proceeds in two phases: first, the agent learns with explicit budget state injection and structured reasoning prompts under linearly decaying budgets; second, the scaffold is removed and the agent adapts to randomly sampled budgets that match deployment conditions. The reward combines answer accuracy and budget efficiency, with adaptive weighting to emphasize efficiency for high‑accuracy queries and reduce it for low‑accuracy ones. Experiments on seven QA benchmarks demonstrate that AnySearch outperforms baselines across all budget scales, generalizes to unseen constraints, and improves tool productivity without excessive token overhead.
arXiv:2606. 07074v1 Announce Type: cross Abstract: Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost.
arXiv:2606. 02373v1 Announce Type: new Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked.
arXiv:2607. 23765v1 Announce Type: cross Abstract: Large language models (LLMs) achieve impressive performance across multiple domains, but using the most capable model for every query is prohibitive at scale.
The paper introduces Task Specialization Fine-Tuning (TSFT), an online framework that allocates a limited fine‑tuning budget across multiple task regions in Contextual Reinforcement Learning. TSFT predicts fine‑tuning performance with a simple parametric model and solves the budget allocation problem exactly using integer linear programming. Experiments on combinatorial optimization, continuous control, and LLM fine‑tuning show that TSFT outperforms baselines in task coverage and approaches oracle performance.
arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.
arXiv:2607. 06223v1 Announce Type: new Abstract: Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of intermediate decisions before receiving a final outcome.
arXiv:2605. 11611v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from outcome-only supervision.
IterSynth introduces a role-decoupled, iterative synthesis framework for deep search agents, separating planning and synthesis into distinct Planner and Synthesizer modules that maintain a persistent summary state. This design mitigates role coupling and context noise, while the new Role-Decoupled Policy Optimization (RDPO) enhances training by combining outcome rewards with turn-level rubric evaluations. Experiments on five long-horizon benchmarks show IterSynth-8B outperforming prior ≤8B agents by 4.2% and delivering significant zero-shot gains over ReAct on proprietary models.
arXiv:2606. 10709v1 Announce Type: cross Abstract: The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards.
The paper introduces ExTS, a tree‑search policy designed for budget‑constrained agentic search where evaluation and generation costs are high. ExTS treats expansion as a value‑of‑information decision, combining discriminative reward shaping, a stochastic virtual child, and quality‑conditioned branching to allocate budget more effectively. Experiments on prompt optimization, code generation, molecular structure elucidation, and agentic workflow optimization show ExTS matching or surpassing task‑specific baselines with an average gain of +5.5% using a single configuration, and the authors also present pilot‑run diagnostics to guide adaptation to different problem structures.
GAMMA is a post‑training framework that learns module‑wise precision preferences for mixed‑precision quantization of large language models. It optimizes a teacher‑forced hidden‑state reconstruction objective under an augmented Lagrangian constraint and then projects the learned preferences into exact budget‑feasible discrete assignments via integer programming. Because the learned preferences encode a stable sensitivity ranking, a single training run can be reused for any deployment budget, reducing per‑budget adaptation from hours to minutes and outperforming fixed‑precision baselines and search‑based methods on Llama and Qwen models.
arXiv:2609.01573v1 Announce Type: cross Abstract: How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open...