Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for external tools. Tool use here is a three-part prob...
arXiv:2606. 03892v1 Announce Type: cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns.
arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-pat...
arXiv:2607. 14171v1 Announce Type: new Abstract: Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes.
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
KnowGPO introduces a reinforcement learning framework that groups search agent trajectories by the task-relevant knowledge they acquire, rather than by surface observations. By decomposing required information into atomic knowledge conditions and using the incremental knowledge gain as a process reward, KnowGPO provides finer-grained credit assignment for deep search tasks. Experiments on Xbench, BrowseComp-ZH, and GAIA demonstrate that KnowGPO outperforms outcome-only and process-supervision baselines by 3.8 to 4.2 points, with an 8B model rivaling or exceeding most 32B open-source systems.
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obs...
The paper introduces Reinforcement Learning with Verifiable Rewards (RLVR) applied to small search agents, specifically training a Qwen3.5-0.8B model with Group Relative Policy Optimization and an interleaved Wikipedia-search tool on the MuSiQue dataset. Experiments varying reward shapes across three seeds show that RLVR can achieve a 3.8‑fold improvement over an untrained baseline, with the best run reaching a 0.352 average exact match. The study finds that the sparse exact‑match reward, standard in larger models, performs poorly for small models, indicating that reward design must be tailored rather than scaled down from large‑model recipes.
MATCH is a closed‑loop framework for model‑aware tool learning that combines curriculum scheduling with hierarchically gated rewards. It introduces Model‑Aware Curriculum Learning (MACL), which dynamically adjusts sample difficulty based on reward signals, and Hierarchical Tool‑call Gated Reward (HTGR), which allocates credit at the tool name, argument key, and argument value levels only when prerequisites are met. Experiments on API‑Bank and BFCL V3 show MATCH achieving 72.19% and 62.87% overall accuracy, outperforming both supervised and RL‑based baselines across multiple backbone models.
Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning proposes TreeOPSD, a critic‑free framework that treats each interaction turn as a tree node, branches alternative continuations, and recursively backs up terminal rewards to generate implicit turn‑level credit. The method maps this credit to a bounded teacher distribution based on the likelihood ratio to a frozen behavior policy, and minimizes the divergence between teacher and student to recover policy‑gradient directions while limiting updates across mini‑batches. Empirical results show TreeOPSD enhances agentic performance on long‑horizon benchmarks, notably improving Qwen3‑30B‑A3B‑Thinking‑2507’s accuracy by 4.97 points over GRPO in the Deep Research setting.