R$^2$ Flow is a recursive self‑improvement framework for large‑language‑model agents that alternates policy learning, independent verification, and versioned skill‑library updates on a shared‑state orchestration graph. By merging histories that differ only in the order of independent steps, it pools evidence across equivalent executions and uses flow‑share readouts, signed utility ranks, verifier evidence, and residual‑variance plateaus to decide when and which skills to edit. Experiments on question answering, mathematical reasoning, interactive decision making, and code generation show that R$^2$ Flow improves task accuracy and library‑edit precision compared to heuristic orchestration, reinforcement learning, and other skill‑evolution baselines, and it transfers across different executors.
By Mingda Zhang, Qiang Huang, Yanjin Li, Zijia Wang, Qika Lin, Xiaoying Tang, Tiesunlong Shen
The paper introduces POrchestra, a proactive agentic orchestration framework that lets sub‑agents request harness adjustments during execution, enhancing adaptability to dynamic environments. It also proposes On‑Policy Orchestration Distillation (OPOD), which uses hindsight feedback from sub‑agents’ requests to provide targeted improvement signals for training the orchestration policy. Experiments on three long‑horizon benchmarks show that POrchestra boosts task success by about 9.1% over the best baseline, and with OPOD the improvement rises to 10.0%, while also improving cost‑performance trade‑offs.
By Xueyang Feng, Chaozhuo Li, Xiaohe Bo, Jiakai Tang, Chenxi Li, Qiwei Ye, Xu Chen
arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.
By Zefeng Wang, Minxi Yan, Jinhe Bi, Sikuan Yan, Volker Tresp, Yunpu Ma
arXiv:2610.19868v1 Announce Type: cross
Abstract: Training LLM agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification...
By Tianyu Liu, Davide Belli, Bence Major, Arash Behboodi, Tribhuvanesh Orekondy
arXiv:2609.37633v1 Announce Type: cross
Abstract: The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards...
By Michael Kirchhof, Eleonora Gualdoni, Andrew Szot, Khashayar Gatmiry, Aryo Lotfi, Abbas Kazerouni, Omar Attia, Sanjoy Chowdhury, Alexander Toshev
EvoSteer introduces an online self‑evolving graph orchestration framework that continuously builds and repairs a team of tool‑using agents during execution. It employs Anchored Trajectory Balance (AnchorTB), a regression‑style loss that assigns credit to each orchestration action by comparing subtrajectories to a frozen reference, and Validated Skill Admission, which tests candidate skills before promotion. Experiments on twelve datasets demonstrate that EvoSteer outperforms existing baselines in question answering, mathematical reasoning, code generation, and interactive decision making.
By Mingda Zhang, Hanwen Zhang, Qiang Huang, Zijia Wang, Pengfei Guo, Yuchen Zhang, Jionghao Zhu, Xiaoying Tang
Rep2Skill introduces a representation-guided framework that enables large language model agents to self-evolve their textual skills by analyzing internal representation trajectories from agent rollouts. The method identifies execution turns that deviate from successful dynamics and uses these signals, together with execution contexts, as actionable feedback for targeted skill revision. Experiments with two open-source LLMs across two agent environments demonstrate that Rep2Skill consistently outperforms purely text-based approaches, showing that incorporating internal representations can enhance agent self-improvement.
By Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren
arXiv:2606. 18837v1 Announce Type: cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks.
By Hehai Lin, Qi Yang, Chengwei Qin
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Workin...
The paper introduces Recuris, a recursive Experiential‑Working Memory architecture that lets long‑horizon agents track task progress and select skills based on current needs rather than full history. By coupling working memory with experiential memory, execution becomes structured evidence that localizes failures to specific memory components, enabling a bounded recursive memory‑evolution loop. Across four benchmarks and ten models, Recuris improves task success in 35 of 37 model‑benchmark pairs, raising state‑of‑the‑art performance on tau‑bench and SkillFlow and reducing common long‑horizon failures by up to 80%.
By Zhaochen Yu, Yingcheng Wu, Zhenfei Yin, Kaiyuan Chen, Zhe Zhao, Mengdi Wang, Shuicheng Yan, Ling Yang
The paper introduces Multi-Agent Self-Supervision (MASS), a recursive self‑improvement technique that alternates between evolutionary workflow optimization and supervised fine‑tuning on self‑generated multi‑agent trajectories. MASS enables a single base model to iteratively propose, execute, and self‑evaluate complex multi‑agent workflows, discovering effective roles and information routing. Experiments with Qwen3.6‑27B show 1.2–1.6× higher performance per output token on four open‑ended benchmarks, and student models trained on MASS traces outperform single‑agent students trained on 1.4× more tokens.
By Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Somayeh Sojoudi, Matei Zaharia, Yujin Tang
SPADE (Self-Play in Adaptive Synthetic Executable Environments) is a reinforcement‑learning framework where a single large language model acts as both an Environment Designer—creating executable, long‑horizon training environments—and a Reasoning Agent—learning to act within those environments. The framework uses a regret signal based on the difference between rewarded performance with and without privileged hints to guide the Designer toward environments that are challenging yet solvable. Experiments show that, when scaled to 30‑billion‑parameter models, SPADE outperforms fixed‑environment baselines by significant margins across math, science, code, and reasoning benchmarks, and improves tool‑use performance on BFCL‑v4 and ACEBench‑Agent.
whyItMatters":"By making environment design a learnable component, SPADE enables continuous self‑improvement and demonstrates that adaptive, self‑generated training environments can substantially boost language‑model performance across diverse tasks."
By Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques