LEAP: Learning Efficient Action Proposals For LLM Agents proposes a method to speed up large language model agents by training a small 0.6B drafter to predict target actions accurately. The approach uses a latency framework that balances drafting, verification, and execution costs, achieving up to 60% faster end‑to‑end wall clock time without reducing task success. LEAP can be online trained, eliminating the need for prior trace collection and making it practical for real‑world deployment.
By Zhen Xu, Qizheng Zhang, Gerry Wan, Shang Zhu, Ce Zhang
arXiv:2605. 03195v2 Announce Type: replace Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search, debugging or terminal execution.
By Spandan Garg, Vikram Nitin, Yufan Huang
arXiv:2606. 10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes.
By Shardul Bansal, Seth Schilbe, Jarrod Barnes
arXiv:2605.09252v3 Announce Type: replace
Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and l...
By Chung-En Sun, Linbo Liu, Ge Yan, Zimo Wang, Tsui-Wei Weng
StoreBench is a live‑commerce environment where an autonomous agent runs a mid‑size online apparel store on a production‑grade backend, facing continuous customer orders, supplier price changes, and market shocks. The agent uses the same 29 merchant tools as a human operator, with a windowed operation budget that ties simulated time to actions, ensuring that model latency does not affect the simulation. Seven large language models were evaluated across 11 scenarios of 30–45 days and a full simulated year, but none matched the scripted smart‑triage policy, and human experts outperformed all models.
By Daksh Raghuvanshi, Ved Vedere, Yifan Wang
The paper investigates how trajectory fine‑tuning can enhance small language models (SLMs) as next‑action controllers in retrieval‑augmented question answering. By building a seven‑way action‑prediction task from teacher search traces, the authors fine‑tune SLMs and cross‑lingual SLMs (xSLMs) using LoRA and evaluate on 1,646 held‑out examples, achieving a macro‑F1 of 0.6536 with Granite 4.1 3B. In an end‑to‑end controller/generator swap experiment on 149 trajectories, the fine‑tuned model improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295, demonstrating that trajectory supervision boosts action prediction and evidence‑recording behavior.
By Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer, Jelena Mitrovi\'c
arXiv:2608. 06557v1 Announce Type: cross Abstract: The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests.
By Muhammad Adnan, Rohan Mahapatra, Prashant J. Nair, Daniel Berger, Pantea Zardoshti, Rodrigo Fonseca, Esha Choukse
arXiv:2608. 05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic.
By Jie Wu, Ming Gong, Feixiang Cheng, Qinqin Zhao
arXiv:2606. 03077v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors.
By Kaiwen Chen, Xin Tan, Jingzong Li, Hong Xu
EarlyEval introduces a lightweight framework that predicts an LLM agent’s final outcome early in its execution, allowing the run to halt when a LightGBM classifier reaches a calibrated confidence threshold. By training success and failure classifiers on behavioral, textual, and reference-solution features, EarlyEval can cut 13%-26% of agent steps and up to 44.1% of input tokens while maintaining 89%-97% prediction accuracy. Across three benchmarks—SWE-bench Verified, TerminalBench, and Toolathlon—this approach reduces evaluation costs with minimal impact on per-agent resolve rates.
By Yuling Shi, Zhensu Sun, Junsen Dong, Chengcheng Wan, David Lo, Xiaodong Gu
The paper introduces EvoResearcher, a training‑free, inference‑time protocol that enables a frozen large language model to perform cost‑bounded self‑reflection and early stopping. By iterating through generate → self‑critique → revise steps until a maximum depth or a CONFIRMED sentinel is reached, the model can self‑verify its answers within a strict compute budget. The protocol incorporates four self‑reflective meta‑reward components—correctness, efficiency, reflection depth, and tool‑call diversity—implemented as prompt‑level mechanisms, and is validated on Big‑Bench Hard, GSM8K, and MATH benchmarks, achieving comparable accuracy while terminating 82‑88% of items early with only about 2.1 generations per question.
By Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li
The paper reports on training and calibration experiments for three open models on the ARC‑AGI‑2 benchmark, using offline runs on four L4 GPUs for up to 12 hours. For the NVARC Qwen3‑4B grid model, a curated corpus of 12,000 executable rules and 95,993 tasks was built, and fine‑tuning on 1,920 real task records raised the semi‑private score from 28.96 to 33.06, with no synthetic‑task checkpoint outperforming the real‑task model. For the Qwen3.8‑27B reasoning model, fine‑tuning on 1,036 of its own reasoning traces and a specialized inference procedure increased the score from 26.81 to 44.03, while the Qwen3.8‑Flash‑Next mixture‑of‑experts model achieved a best score of 56.67 after expert pruning, routing statistics adaptation, and an FP8 indexer cache.
By Nguyen Minh Thang, Trinh Thi Phuong