The paper introduces TRACE, a digital‑advertising diagnostic environment that uses simulated interventions to generate verifiable rewards for training reasoning agents. By injecting controlled interventions into a simulator, the hidden cause of anomalies becomes an oracle label, enabling agents to learn to identify root causes and affected segments through noisy, confounded evidence. Experiments show that reinforcement learning with these synthesized rewards outperforms large prompted baselines, achieving higher accuracy while using fewer tool calls.
By Rui Sun, Zhan Shi, Bing He
RECAST is a new framework that generates datasets with far more constraints per example than existing benchmarks, aiming to push large language models (LLMs) to better follow complex instructions. The authors built RECAST-30K, a 30,000‑instance dataset covering 19 constraint types extracted from real prompt‑response pairs, and showed that fine‑tuning on it improves LLMs’ ability to handle complex tasks without harming general performance. RECAST also provides rule‑based and LLM‑based validators for automatic constraint verification, enabling reward‑based reinforcement learning to further enhance model performance on challenging tasks.
By Zhengkang Guo, Wenhao Liu, Mingchen Xie, Jingwen Xu, Zisu Huang, Muzhao Tian, Jianhan Xu, Yuanzhe Shen, Qi Qian, Muling Wu, Xiaohua Wang, Changze Lv, He-Da Wang, Hu Yao, Xiaoqing Zheng, Xuanjing Huang
The paper introduces CIG‑SFT, a supervised fine‑tuning method that uses conditional information gain to evaluate how much each demonstrated token reduces uncertainty about the task. By comparing token likelihoods from a frozen reference model with and without task input, the method derives a KL‑regularized projection of the current policy, yielding a scalar‑weighted SFT objective whose gradients match the projected target. Experiments on mathematical reasoning and code‑generation benchmarks show that CIG‑SFT outperforms standard SFT and adaptive fine‑tuning baselines, especially in generalizing to challenging evaluation distributions, without requiring extra data or online rollouts.
By Yuxuan Gu, Kequan Niu, Xiaocheng Feng, Yun Li, Yiqiao Yang, Bing Qin
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao
The study investigates how language models acquire in-context learning (ICL) by distinguishing between copying a nearby demonstration and integrating information across a prompt. Across 17 models, roughly one-third default to copied answers, a few are undecided, and the remainder favor rule-consistent answers that yield higher accuracy and are guided by the requested value rather than the nearest conflicting example. Analyses show that models prioritize task-relevant prompt tokens before accuracy surpasses chance, and that synthetic or fine-tuned training can shift models toward compositional responses or improve accuracy when prompts reassign label meanings.
By Minglai Yang, Xinyu Guo, Renxiong Wang, Sunjie Hou, Daniel Yue Zhang, Yunzhong He
arXiv:2608. 12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, output schemas.
By Mariya I. Vasileva
LIFT introduces Lift-Bench, a new instruction‑following benchmark that asks language models to draft a document based on a topic and a structured outline, with constraints scoped to specific sections for finer control. The benchmark includes both verifiable and judged constraints and a training counterpart, Lift‑Train, designed to reduce reward hacking by providing both main‑task and instruction‑following constraints. Experiments show that state‑of‑the‑art models struggle with the harder subsets, and training on Lift‑Train is less prone to reward hacking than traditional IF training.
By Eran Goldstein, Yuval Belfer, Yonatan Belinkov, Daniel Gissin
arXiv:2607. 03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments.
By Jou Barzdukas, Jack Peck, Julian Schulz, Paulius Rauba, Steven Basart, Lennie Wells
CAST is a critique‑aware training framework that transforms sparse task outcomes into action‑level supervision for both critique learning and policy optimization. By analyzing agent trajectories, CAST synthesizes structured rationales that explain action validity under partial observability, enabling the creation of richer training data. Fine‑tuned Qwen3‑family models trained with CAST show significant reliability gains, outperforming GPT‑OSS‑120B by over 10% on Retail tasks and improving Telehealth performance by 9% in an out‑of‑domain setting.
By Amir Saeidi, Zehua Zhang, Rishitosh Singh, Naman Ahuja, Vivek Gupta, Ali Payani, Gaowen Liu, Jayanth Srinivasa, Chitta Baral
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.
By Victor Ye Dong, Reid Pryzant, Yi Liu, Jian Jiao
arXiv:2606. 20659v2 Announce Type: replace Abstract: Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance.
By Boyin Tan, Xiaowei Huang, Youcheng Sun
arXiv:2602.21189v3 Announce Type: replace-cross
Abstract: Pass@$k$ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, an...
By Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi