CORTEXA
← Browse
arxivcs.LGcs.AIcs.CL2026-06-28

From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training

Zishang Jiang, Tingyun Li, Jinyi Han, Xinyi Wang, Sihang Jiang, Yizhou Ying, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extracts low-variance learning signals from the Wasserstein distance between them. We theoretically and empirically show that aggregating semantically similar states and actions in the intent space yields a bounded-variance estimator and improves policy performance stably. Our code is available online.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CL2026-06-30

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge

LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision m…

View free PDFSource page
arxivcs.AIcs.CLcs.LG2026-06-28

Selective Memory Retention for Long-Horizon LLM Agents

Pranath Reddy

When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in frozen LLM agents that scores entries by interpretable features (success, age, access frequency, redundancy, specificity, similarity,…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.OS2026-07-19

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

Ryan Xu, Atlas Zhao, David Bao, Frank Du

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrain…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-01

CausalMix: Data Mixture as Causal Inference for Language Model Training

Zinan Tang, Yukun Zhang, Shaomian Zheng, Zhuoshi Pan, Qizhi Pei, Dingnan Jin, et al.

In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As a result, when the underlying data pool shifts, th…

View free PDFSource page
arxivcs.CVcs.AIcs.CLcs.LG2026-07-09

Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing

Feng Wang, Canmiao Fu, Zhipeng Huang, Chen Li, Jing Lyu, Ge Li

Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialog…

View free PDFSource page
arxivcs.LGcond-mat.mtrl-scics.AIcs.CL2026-06-28

Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents

Kyungmin Nam, Seunghee Han, Jihan Kim

Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine-learning models reveal little about why a structure succeeds. We introduce LLM4MOF, a closed-loop framework in which language-mod…

View free PDFSource page