Offline goal-conditioned reinforcement learning (GCRL) offers a practical learning paradigm in which goal-reaching policies are trained from abundant state-action trajectory datasets without additional environment interaction. However, offline GCRL still struggles with long-horizon tasks, even with recent advances that employ hierarchical policy structures, such as HIQL [33]. Identifying the root cause of this challenge, we observe the following insight. Firstly, performance bottlenecks mainly stem from the high-level policy's inability to generate appropriate subgoals. Secondly, when learning the high-level policy in the long-horizon regime, the sign of the advantage estimate frequently becomes incorrect. Thus, we argue that improving the value function to produce a clear advantage estimate for learning the high-level policy is essential.

Real-world robotic tasks often require agents to achieve sequences of goals while respecting time-varying safety constraints. However, standard Reinforcement Learning (RL) paradigms are fundamentally limited in these settings. A natural approach to these problems is to combine RL with Linear-time Temporal Logic (LTL), a formal language for specifying complex, temporally extended tasks and safety constraints.

The ability to actively acquire information is essential for open-world planning under partial observability and incomplete knowledge. However, most existing embodied AI systems either assume a known object category or rely on passive perception strategies that exhaustively gather object and relational information from the environment. Such a strategy becomes insufficient in visually complex open-world settings. For instance, a typical household may contain thousands of novel and uniquely configured objects, most of which are irrelevant to the agent's current task. Consequently, open-world agents must be capable of actively identifying and prioritizing task-relevant objects to enable efficient and goal-directed knowledge acquisition. In this work, we introduce ACTIVEVOO, a novel zero-shot framework for open-world embodied planning that emphasizes object-centric active knowledge acquisition. ACTIVEVOO employs lifted regression to generate compact, first-order subgoal descriptions that identify task-relevant objects, and provides a principled mechanism to quantify the utility of sensing actions based on commonsense priors derived from LLMs and VLMs. We evaluate ACTIVEVOO on the visual ALFWorld benchmark, where it achieves substantial improvements over existing LLMand VLM-based planning approaches, notably outperforming VLMs fine-tuned on ALFWorld data. This work establishes a principled foundation for developing embodied agents capable of actively and efficiently acquiring knowledge to plan and act in open-world environments.

Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge in reinforcement learning (RL). Linear temporal logic (LTL) offers a unified formalism to specify such requirements, yet existing methods are limited in their abilities to handle nested long-horizon tasks and safety constraints, and cannot identify situations when a subgoal is not satisfiable and an alternative should be sought. In this paper, we introduce GenZ-LTL, a method that enables zero-shot generalization to arbitrary LTL specifications.

Web navigation is a unique domain that can automate many repetitive real-life tasks beyond and typical is challenging multimodal as lar it ge requires language long-horizon model (MLLM) sequential tasks.

Long-horizon planning in robotic manipulation requires translating under-specified, symbolic goals into executable control programs that satisfy spatial, temporal, and physical constraints.

Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge in reinforcement learning (RL). Linear temporal logic (LTL) offers a unified formalism to specify such requirements, yet existing methods are limited in their abilities to handle nested long-horizon tasks and safety constraints, and cannot identify situations when a subgoal is not satisfiable and an alternative should be sought. In this paper, we introduce GenZ-LTL, a method that enables zero-shot generalization to arbitrary LTL specifications.

Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated theorem proving. Surprisingly, we discover that even without any training, careful neuro-symbolic coordination of existing off-the-shelf reasoning models and tactic step provers can achieve comparable performance. This paper introduces DSP+, an improved version of the Draft, Sketch, and Prove framework, featuring a fine-grained and integrated neuro-symbolic enhancement for each phase: (1) In the draft phase, we prompt reasoning models to generate concise natural-language subgoals to benefit the sketch phase, removing thinking tokens and references to human-written proofs; (2) In the sketch phase, subgoals are autoformalized with hypotheses to benefit the proving phase, and sketch lines containing syntactic errors are masked according to predefined rules; (3) In the proving phase, we tightly integrate symbolic search methods like Aesop with step provers to establish proofs for the sketch subgoals. Experimental results show that, without any additional model training or fine-tuning, DSP+ solves 80.7%, 32.8%, and 24 out of 644 problems from miniF2F, ProofNet, and PutnamBench, respectively, while requiring fewer budgets compared to state-of-the-arts. DSP+ proves imo p1, an IMO problem in miniF2F that is not solved by any prior work. Additionally, DSP+ generates proof patterns comprehensible by human experts, facilitating the identification of formalization errors; For example, eight wrongly formalized statements in miniF2F are discovered. Our results highlight the potential of classical reasoning patterns besides the RL-based training. All components will be open-sourced.

A.1 MCTS-kSubS algorithm In Algorithm 4 we present a general MCTS solver based on AlphaZero. Solver repeatedly queries the planner for a list of actions and executes them one by one. Baseline planner returns only a single action at a time, whereas MCTS-kSubS gives around kactions - to reach the desired subgoal (number of actions depends on a subgoal distance, which not always equals k in practice). MCTS-kSubS operates on a high-level subgoal graph: nodes are subgoals proposed by the generator (see Algorithm 3) and edges - lists of actions informing how to move from one subgoal to another (computed by the low-level conditional policy in Algorithm 2). The graph structure is represented by treevariable. For every subgoal, it keeps up to C3 best nearby subgoals (according to generator scores) along with a mentioned list of actions and sum of rewards to obtain while moving from the parent to the child subgoal. Most of MCTS implementation is shared between MCTS-kSubS and AlphaZero baseline, as we can treat the behavioral-cloning policy as a subgoal generator with k = 1. MCTS-kSubS and the baseline are encapsulated in GEN_CHILDREN function (Algorithms 5 and 6).