The paper introduces GUIDER, a method that jointly trains a decision flow controller and a reasoning policy to improve clinical guideline reasoning. GUIDER generates multiple plausible decision flows from guideline supervision, computes process rewards across these flows, and gates them on answer correctness to address both path–answer gaps and path multiplicity. Experiments on MedGUIDE and out‑of‑domain benchmarks show that GUIDER outperforms existing reinforcement learning baselines, achieving higher weighted accuracy and guideline adherence.
By Gaurav Bhatt, Marinka Zitnik
arXiv:2605. 29668v2 Announce Type: replace Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment.
By Johannes Moll, Jean-Philippe Corbeil, Jiazhen Pan, Martin Hadamitzky, Daniel Rueckert, Lisa Adams, Keno Bressem
arXiv:2606. 10120v1 Announce Type: cross Abstract: Postprandial hyperglycemia is a key risk factor for metabolic disorders; however, existing dietary guidance is often static, impractical, and insufficiently personalized, providing recommendations that are difficult to follow or not impactful.
By Asiful Arefeen, Carol Johnston, Hassan Ghasemzadeh
ShanLiangRen is a nutrition agent designed to generate personalized daily meal plans that satisfy both user constraints and multidimensional nutritional goals. It transforms dietary specifications, nutrient data, user attributes, and natural language requirements into a constrained planning instance, then uses a retrieval‑augmented generation approach to narrow the candidate set from a large ingredient and recipe space. Finally, it refines plans via Pareto‑guided iterative revisions with an LLM, producing fully quantified meal plans with explicit ingredients, portion sizes, and compliance reports.
By Miao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu, Chunli Lv
arXiv:2609.38142v1 Announce Type: new
Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advi...
By Rishabh Agrawal, Hejie Cui, Shasha Li, Shanchan Wu, Sercan \"{O}. Ar{\i}k
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:2606. 04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach.
By Kaustav Kundu, Ritvik Shrivastava, Maxim Arap, Nanshu Wang, Xianhui Zhu, Quintin Fettes, Gautam Tiwari, Parth Suresh, Th\'eo Moutakanni, Alejandro Castillejo Munoz, Allen Bolourchi, Pascale Fung, Pinar Donmez, Babak Damavandi, Anuj Kumar, Seungwhan Moon
arXiv:2608.16831v2 Announce Type: replace
Abstract: Pretrained large language models offer a practical foundation for learning useful behavior from few task-specific examples. We argue that current p...
By Minh-Ha Nguyen, Ngoc-Ngo Quang Tran, Thuy Dung Nguyen, Cathy Shyr
RGDT-Bench is a new benchmark that evaluates large language models on Rule‑Governed Decision Tasks, where models must apply external rules to facts, justify decisions, and provide checkable justifications. The benchmark offers 202.1K condition‑level supervision slots across four task tracks and eight task‑probe combinations, and it labels warrant completeness through label‑blind extraction and deterministic checks. Evaluation shows that among correct responses, 40.2% of warrants are incomplete, and existing evaluators struggle to detect this, prompting the authors to train a reward model that improves AUROC to 69.24% and outperforms outcome‑supervised baselines.
The paper argues that large language model agents should not be the sole authority on whether they have satisfied a task. It identifies two gaps—understanding–execution and state–authority—where agents may claim completion without actually meeting the specification. The authors propose SpecHarness, a framework that separates agent proposals from authoritative state by requiring evidence from qualified providers to confirm compliance, and demonstrate its effectiveness on guideline‑following and artifact‑generation tasks.
By Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang
DMAIC-Bench is a new benchmark that tests large‑language‑model agents on their ability to exercise self‑restraint—deciding when to continue, redirect, or stop a multi‑stage analytical task based on intermediate evidence. It contains 97 seeded tasks across 15 industrial cases in four sectors, with paired counterfactual variants that require opposite actions to distinguish warranted restraint from indiscriminate stopping. Evaluation involves a private scorer for execution traces and independent expert review, revealing that while agents often route correctly on GO decisions, they frequently act on invalid evidence at NO‑GO decisions, with a 47% average error rate.
whyItMatters":"The benchmark provides a systematic way to measure whether agents can appropriately use evidence to control their own actions, a capability that current benchmarks largely overlook."
By Shan Peng, Shuaiqi Cheng, Miao Peng, Chenyi Zi, Jia Li
The paper investigates how fine‑tuned language agents can selectively withdraw actions when evidence changes or authority is revoked. Using a synthetic NAQD‑Env environment, the authors compare an original curriculum with an enriched one across multiple system‑prompt framings and evaluate four LoRA checkpoints of Qwen2.5‑3B‑Instruct against instruction‑tuned baselines. Results show that fine‑tuned checkpoints achieve higher decision agreement and withdrawal recall, reduce incorrect withdrawals, and narrow prohibited combinations, though they also omit valid event reports and exhibit mixed preservation of authorized actions.
By Mohamed Abouzahra