Strongest Prior Asynchronous Baseline

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 23

All topics

GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents
Sep 28, 2026Haodong Zhu, Yangyang Ren, Changbai Li +4Group-Based Reinforcement Learning Credit Assignment
Beihang University · Zhongguancun Academy · Communication University of China +1
Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translation
Sep 28, 2026Thodsaporn Chay-intr, Krittapad Harnchang, Mahannop +3Machine Translation Data-Curation
iApp Technology, Thailand · Intelligent Informatics and Service Innovation Research Center, Thailand · Artificial Intelligence Entrepreneur Association of Thailand (AIEAT), Thailand +1
SPINET: Sheaf Protein Inverse Folding Network
Sep 28, 2026Jens Lundsgaard, Colin Mikulski, Zhixuan Yan +1Protein Structure Prediction Protein
Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI, USA · Department of Mathematics, University of Wisconsin–Madison, Madison, WI, USA · Department of Biomedical Engineering, University of Wisconsin–Madison, Madison, WI, USA +4
FLARE: Flow Matching with Local Axis-Angle Representations for Stochastic Micromagnetic Evolution
Sep 28, 2026Pengyu Li, Renjie Tong, Xuanlue Jiang +2Magnetic Tunnel Junction Strongest Prior Asynchronous Baseline
State Key Laboratory of Quantum Functional Materials, Department of Physics, and Guangdong Basic Research Center of Excellence for Quantum Science, Southern University of Science and Technology, Shenzhen 518055, China
Program-Verified Self-Evolution for Vision-Language Models
Sep 27, 2026Ahmed Heakl, Sungik Choi, Moontae Lee +1Recent Vision-Language Models Qwen3
LG AI Research · MBZUAI · University of Illinois at Chicago +1
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
Sep 16, 2026Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao +2Speculative Decoding LLM Inference Optimization
University of Southern California, Los Angeles, CA, USA
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia Smith +2Poisoning Attacker Large Language Model
Carnegie Mellon University · Anthropic
HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
Sep 9, 2026Jianzhi Shen, Keyu Mao, Minghao Shao +7Large Language Model Personalization Personalization
Johns Hopkins University · Institute of Science Tokyo · NYU Tandon +1
Generative Learning for Quantum Measurement Design
Aug 11, 2026Jun Dai, Olivier Nahman-Lévesque, Guillaume Rabusseau +2Entanglement Generative Models
Mila – Québec AI Institute, Montréal, QC, Canada · Département d’informatique et de recherche opérationnelle, Université de Montréal, Montréal, QC, Canada · Institut quantique, Université de Sherbrooke, Sherbrooke, QC, Canada +3
An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting
Aug 3, 2026Fariba Dehghan, Sebastian Stein, Vahid Yazdanpanah +2Energy Forecasting Atmospheric Dynamics
University of Southampton
Bole: Efficient Tree Speculation for Hybrid-Attention Language Models
Aug 3, 2026Li Wang, Yi Su, Xiabao Wu +9Speculative Decoding Self-Speculative
State Key Laboratory for Novel Software Technology, Nanjing University · Ant Group · Shanghai Jiao Tong University +1
LeAct: Learning to Reason from Expert Actions
Jul 23, 2026Ziran Yang, Chengshuai Shi, Raj Ghugare +3Reasoning Skills Reinforcement Learning Baseline
Princeton University
Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis
Jul 22, 2026Adel ElZemity, Shujun Li, Budi AriefMalware Small Large Language Models
University of Kent, Canterbury, United Kingdom
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
Jun 15, 2026Alper YıldırımLong-Horizon Forecasting Asymmetric Grouped-Attention Variate Mixer
ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
Jun 4, 2026Rahul Suresh Babu, Laxmipriya Ganesh IyerControlling Tool Use Large Language Model Agents
Independent Researcher United States of America
Hinge Regression Trees and HRT-Boost: Newton-Optimized Oblique Learning for Compact Tabular Models
May 22, 2026Hongyi Li, Jun Xu, Hong YanDecision Trees Tabular Learning
School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, 518055, China and with the Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Shenzhen, 518055, China · Department of Electrical Engineering, City University of Hong Kong, Kowloon, Hong Kong
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
May 12, 2026Sunung Mun, Sunghyun Cho, Jungseul OkStrongest Prior Asynchronous Baseline Inference-Time Steering
Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science & Engineering, POSTECH
A Quantum Inspired Variational Kernel and Explainable AI Framework for Cross Region Solar and Wind Energy Forecasting
May 9, 2026Pavan Manjunath, Thomas PruferOffshore Wind Turbine Photovoltaic
Independent Research Scholar, Germany
HyperTransport: Amortized Conditioning of T2I Generative Models
May 7, 2026Valentino Maiorca, Eleonora Gualdoni, Xavier Suau +3Linear Activation Steering Stable Transport
1ISTA · 2Apple
Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video
May 2, 2026Jiantang HuangVideo Temporal Grounding Accidents
Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
Mar 6, 2026Haiqing Hao, Zhipeng Sui, Rong Zou +4Object Detection Dynamic Sparse Attention
State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing, China · Robotics and Perception Group, University of Zurich, Zurich, Switzerland · ShanghaiTech University, Shanghai, China
Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation
Feb 24, 2026Ji Dai, Quan Fang, DeSheng CaiMultimodal Recommendation Model Recommendation
Beijing University of Posts and Telecommunications, China · Beijing University of Posts and Telecommunications, Beijing, China · Tianjin University of Technology, China
HauntAttack: When Attack Follows Reasoning as a Shadow
Jun 8, 2025Jingyuan Ma, Rui Li, Zheng Li +4Large Language Model Safety Strongest Prior Asynchronous Baseline
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University · StepFun · Department of Computing, The Hong Kong Polytechnic University +1

Sep 28, 2026, cs.LGJ/K move · Enter open · S save

GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents

Haodong Zhu, Yangyang Ren, Changbai Li, Sheng Xu+3

Beihang University · Zhongguancun Academy · Communication University of China+1

Group-Based Reinforcement Learning Credit Assignment Hindsight Graph Representations Strongest Prior Asynchronous Baseline

Open paper AskPDF arXiv

Group-based reinforcement learning (RL) has advanced large language models (LLMs) and is increasingly extending to agentic tasks, where sparse terminal rewards make step-level credit assignment essential. Existing methods assign credit from what follows an action in sampled rollouts, but do not explicitly capture its retrospective relation to the realized outcome. Hindsight credit assignment (HCA) instead attributes credit through the ratio of hindsight to behavior-policy probabilities, but estimating the hindsight distribution requires an auxiliary model or an extra pass. To address this estimation bottleneck, we propose GraphHCA, a model-free realization of HCA that eliminates explicit hindsight-distribution estimation. For terminal-goal tasks with deterministic transitions, Bayes' rule reduces the hindsight ratio to a ratio of behavior-policy success probabilities at consecutive states. Taking logs yields a state-wise success potential, whose increment across a transition provides step-level credit. GraphHCA estimates this potential from pooled rollouts through a discounted recursion on the induced transition graph, which admits a unique fixed point on any directed graph. The resulting step-level signal is combined with the trajectory-level advantage, requiring neither a learned hindsight model nor an extra forward pass and recovering GRPO when the step-level weight is zero. Among all compared baselines, GraphHCA achieves state-of-the-art results on ALFWorld and WebShop at both LLM scales, and on Sokoban with a vision-language agent. For example, on ALFWorld it improves overall success rate by up to 24.6 points over GRPO and by up to 4.7 points over the strongest step-level baseline.

Momentum

Related topics

Latest papers 23