The paper introduces LLM-Guided Contextual Action Evaluation (LCAE), a method that leverages a large language model to transform fixed industrial documents into a frozen action–observation–direction–delay relation basis. Recent numerical action–response history modulates the strength of these relations, creating a state‑conditioned nonlinear action‑effect field that both the actor and critic use for policy learning. LCAE integrates document semantics into maximum‑entropy policy learning without requiring the LLM or embedding model to run online during training or deployment.
Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affect...
The paper introduces PolicyLift, a three‑stage framework that improves decision policies using observational data for complex, structured actions such as text or images. Stage 1 learns discrete action codes that capture high‑level strategies, Stage 2 trains a context‑dependent policy over these codes, and Stage 3 generates full actions conditioned on the learned codes. The authors provide theoretical guarantees that improving the code‑level policy leads to improvement in the original action space and demonstrate consistent policy gains in synthetic and real‑world text generation experiments.
The paper introduces Agentic In-Context Learning (Agentic ICL), a framework where fixed‑parameter Transformers learn from interactions that shape the context they receive. It models an interactive learner with state, update, and decision rules, covering active learning, bandits, and online reinforcement learning, and demonstrates that causal Transformers can approximate these algorithms over a finite horizon. Experiments show that Transformers can learn to execute recursions and that different reward signals produce distinct decision policies, with alignment between process supervision and outcome‑optimal actions influencing learned behavior.
Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was dem...
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
The paper introduces Intention Distillation (INDI), a method that injects behavior-level intent into Vision‑Language‑Action (VLA) model decoders by leveraging a frozen teacher vision‑language model to interpret demonstrations. During training, the teacher processes the current observation, instruction, coarse action summary, and execution video, producing a multimodal intent representation that the VLA decoder uses alongside trajectory and execution features to predict actions. Experiments on SimplerEnv‑Bridge, RoboCasa Kitchen, and real‑world tasks show that INDI consistently improves success rates, especially on longer‑horizon tasks, demonstrating that explicit modeling of semantic intent benefits action decoders.
arXiv:2607. 27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents.
arXiv:2610.16763v1 Announce Type: cross Abstract: Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an acti...
ActionPiece rethinks how actions are tokenized for autoregressive vision‑language‑action models by introducing physical rank consistency (PRC) to evaluate relational fidelity of reconstructed actions. The method jointly supervises representation learning and quantization to preserve local physical distance rankings, improving both PRC and policy success. Experiments on LIBERO, LIBERO‑Plus, SimplerEnv, and VLA‑Arena show significant gains over baseline tokenizers.
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history...
FlexiWorld is a JEPA-based latent world model that learns variable‑length action chunks across multiple time scales for goal‑directed planning. It jointly trains a causal action encoder and an autoregressive actor, using mixed‑span goal supervision and Student Forcing to reduce exposure bias. In experiments on four benchmarks, FlexiWorld with the Actor‑Residual Cross‑Entropy Method (ARCEM) achieves higher mean success rates than the strongest baseline and supports flexible planning chunk lengths without retraining.
The paper investigates when in‑context learning (ICL) can succeed even if the instruction or target task is not covered by a model’s pretraining data. It introduces a theoretical framework that distinguishes two types of distribution shift—unsupported instructions and unsupported target tasks—and shows how demonstrations can mitigate these shifts. The authors further extend the analysis to long‑horizon tasks that can be decomposed into pretraining‑supported subtasks, providing error bounds that explain how ICL can handle tasks beyond the model’s original support.