4arXiv cs.AI (Artificial Intelligence)·
Courteous anticipatory planning reduces multi-robot task costs in shared persistent environments
A new arXiv paper introduces courteous anticipatory planning, a model-based approach for robots sharing a persistent environment to minimize both immediate and expected future task costs across all agents. The method uses factored per-robot learned cost estimators to avoid combinatorial joint rollouts, enabling modular deployment. Evaluated in PDDL-based home and restaurant domains, the approach reduces total cost by up to 17.41% versus myopic planning and 13.24% versus selfish anticipatory planning in multi-robot settings.
Related guides (1)
Related events (8)
PCMA: Learning coordinated agent-specific preferences for multi-objective multi-agent RL
A new arXiv preprint introduces Preference Coordinated Multi-agent Policy Optimization (PCMA), a method for cooperative multi-objective multi-agent reinforcement learning (MOMARL) that learns agent-specific preferences to enable complementary trade-offs across agents. The authors formulate cooperative MOMARL as a team-optimal game and provide a first-order improvement decomposition showing that preference diversity can induce team improvement. Experiments on cooperative MOMA environments and a traffic-control scenario demonstrate improvements in both performance and trade-off coordination.
Two-step constraint programming method for optimal resource scheduling in autonomous laboratory AI agents
A preprint from arXiv introduces a two-step method for resource utilization in autonomous laboratory orchestration, combining constraint programming for optimal scheduling with a status-dependency system for robust execution. The work is demonstrated on a platform for metal-organic framework synthesis, addressing real-world hardware constraints like multi-instrument capacity and throughput. The approach separates the AI agent's role (suggesting experiments) from the scheduling and execution layer, which is a practical systems contribution for lab automation.
planning-with-files: persistent file-based planning layer for AI coding agents
A GitHub project implementing persistent, file-based planning for AI coding agents and long-running agentic tasks using crash-proof markdown plans that survive context loss. The system provides a deterministic completion gate and multi-agent shared state on disk, compatible with Claude Code, Codex CLI, Cursor, Kiro, OpenCode, and 60+ agents via a SKILL.md standard. The project has accumulated 24,602 stars with 61 added today, indicating meaningful community traction.
ProAct: Proactive Agent Architecture Using Idle-Time Compute to Anticipate User Needs
ProAct is a proactive agent architecture that uses idle time between user interactions to predict upcoming needs, pre-fetch information, and resolve knowledge gaps before queries are issued. The system analyzes dialogue history and persistent memory to iteratively acquire relevant information in advance. Evaluated on the new ProActEval benchmark (200 scenarios, 40 domains), ProAct reduces required turns by 14.8%, user effort by 11.7%, and hallucination rates by 28.1% compared to reactive baselines. The work also achieves state-of-the-art reflective accuracy on MemBench.
PACT: Hybrid SLM deliberation architecture improves reactive RL policies in unfamiliar environments
Researchers propose PACT (Plan, Align, Commit, Think), a hybrid architecture pairing a fast reactive RL policy with an asynchronous small language model planner for deliberation. The SLM generates and validates candidate action plans via simulation before committing to execution, bypassing the RL policy without retraining. Evaluated on FrozenLake configurations of increasing difficulty, PACT outperforms baselines using only a 2B-parameter SLM, suggesting complementary strengths between deliberative planning and reactive execution.
Adaptive safety margins for visual robot navigation via context-conditioned safety critic
A new arXiv paper proposes a context-conditioned safety critic that learns adaptive clearance preferences for ranking diffusion-based trajectory proposals in indoor robot navigation. The critic decomposes into safety, efficiency, and distance-constraint matching terms, trained with privileged ESDF geometry in simulation and distilled into a perception-only selector via teacher-student learning. The method achieves top success rate and SPL on PointGoal navigation benchmarks (HM3D, MP3D) and transfers zero-shot to a Unitree G1 humanoid robot without task-specific tuning.
OmniAct: Hierarchical framework for persistent embodied agents with unified cyber-physical action spaces
Researchers present OmniAct, a hierarchical asynchronous architecture for embodied agents that unifies cyber (APIs, IoT) and physical (manipulation, navigation) action spaces under a single multimodal semantic planner. The system incorporates adaptive hierarchical memory with event-boundary-driven compression to maintain sub-linear context growth, and an asynchronous visual preemption engine for closed-loop failure recovery during physical execution. Evaluated across 40 real-world long-horizon tasks on two robotic platforms coordinating four IoT devices, OmniAct achieves consistent end-to-end success improvements and elevates mid-scale open-weight models to proprietary-level performance. The work directly addresses the fragmentation between planning, memory, and verification in existing embodied agent systems.
PRP: Proactive Routing Paradigm for efficient visual reasoning via early difficulty estimation
Researchers introduce PRP (Proactive Routing Paradigm), a method for routing multimodal queries to either a small draft model or a large target model before generating a full output, based on jointly estimated difficulty signals. The approach uses Draft Rating Learning to give the draft model an internal confidence estimator and Joint Rating Learning to predict target model competence, enabling fine-grained instance-level routing. Experiments across multimodal reasoning benchmarks show inference acceleration without accuracy loss. The work addresses a gap in speculative/cooperative inference for vision-language models, where existing language-model routing methods fail.