arXiv AI By Anh Ta, Junjie Zhu, Shahin Shayandeh

PROOF-Gen: From Optimized Data to Better Distillation

Read the original on arXiv AI →

PROOF-Gen is a method that improves distillation of tool‑calling models by recovering successful trajectories from teacher failures. It uses per‑scenario prompt optimization to generate corrective guidance that steers the teacher to a passing trajectory, then removes this guidance before training so the student learns from clean demonstrations. On τ2‑bench, PROOF-Gen recovers 93% of failed scenarios, boosting Qwen3‑4B‑Instruct‑2507’s Pass^1 from 0.132 to 0.529 and improving Gemma 4 E4B‑it by 7.2pp on BFCL v4 multi‑turn, while also raising deployed on‑device model performance by up to 5.0pp across response‑quality metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
5d ago

TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents

TRACE (TRAjectory-Contrastive Evolution) is a self‑evolving skill bank that improves the consistency and limit‑awareness of large‑language‑model agents without changing the model weights. By iteratively refining modular skills based on successful and failed trajectories, TRACE raises consistent performance (Pass^3) on the CAR‑bench in‑car assistant tasks from 59.9 % to 94.5 % on GPT‑5.5 and achieves first place on the hidden set with GPT‑5.6‑Sol. The approach demonstrates that a skill‑based, self‑evolution loop can convert a model’s potential into stable, reliable behavior.

By Wenhao Wu, Menghao Zhang, Xin Wang, Zhi Wang, Kun Shao, Jian Luan
arXiv Machine Learning
Aug 12

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.

By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi
arXiv AI
Jun 18

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier

arXiv:2606. 18284v1 Announce Type: cross Abstract: The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model.

By Lorenz Wolf, Connor Watts, Roger Creus Castanyer, Geoffrey Bradway, Maxwill Lin, Augustine N. Mavor-Parker, Matthew Daborn-Sargent
arXiv AI
Jun 3

Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

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.

By Ibrahim Abdelaziz, Asim Munawar, Kinjal Basu, Maxwell Crouse, Chulaka Gunasekara, Suneet Katrekar, Pavan Kapanipathi
arXiv AI
Jul 7

TREK: Distill to Explore, Reinforce to Refine

arXiv:2607. 05339v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support.

By Yuanda Xu, Zhengze Zhou, Kayhan Behdin, Jelena Markovic-Voronov, Hejian Sang, Xiaomin Li, Wenhui Zhu, Xinchen Du, Aida Rahmattalabi, Ran He, Sen Na, Zhipeng Wang, Alborz Geramifard