In the supplementary, we first discuss the experimental details and hyperparameters in Section A. Section B, and further present the visualization in RLBench in Section C. Finally, we discuss how to MLP with 512 hidden units and Mish activations. The probability ϵ of random actions is set to 0. 03 in Stochastic Environments. So the sampled trajectories still lead to the collision. Figure 1 illustrates a problematic sampled trajectory after execution. We further evaluate the performance with different replanning steps in Table 1.

Given a previously generated plan, how do we effectively regenerate a new plan?

We present a hybrid multi-robot coordination framework that combines decentralized path planning with centralized conflict resolution. In our approach, each robot autonomously plans its path and shares this information with a centralized node. The centralized system detects potential conflicts and allows only one of the conflicting robots to proceed at a time, instructing others to stop outside the conflicting area to avoid deadlocks. Unlike traditional centralized planning methods, our system does not dictate robot paths but instead provides stop commands, functioning as a virtual traffic light. In simulation experiments with multiple robots, our approach increased the success rate of robots reaching their goals while reducing deadlocks. Furthermore, we successfully validated the system in real-world experiments with two quadruped robots and separately with wheeled Duckiebots.

Correctness alone is insufficient: LLM-generated programs frequently satisfy unit tests while violating contest time or memory budgets. We present SwiftSolve, a complexity-aware multi-agent system for competitive programming that couples algorithmic planning with empirical profiling and complexity-guided repair. We frame competitive programming as a software environment where specialized agents act as programmers, each assuming roles such as planning, coding, profiling, and complexity analysis. A Planner proposes an algorithmic sketch; a deterministic Static Pruner filters high-risk plans; a Coder emits ISO C++17; a Profiler compiles and executes candidates on a fixed input-size schedule to record wall time and peak memory; and a Complexity Analyst fits log-log growth (s, R2) with an LLM fallback to assign a complexity class and dispatch targeted patches to either the Planner or Coder. Agents communicate via typed, versioned JSON; a controller enforces iteration caps and diminishing returns stopping. Evaluated on 26 problems (16 BigO, 10 Codeforces Div. 2) in a POSIX sandbox (2 s / 256-512 MB), SwiftSolve attains pass@1 = 61.54% (16/26) on the first attempt and Solved@<=3 = 80.77% with marginal latency change (mean 11.96 s to 12.66 s per attempt). Aggregate run-level success is 73.08% at 12.40 s mean. Failures are predominantly resource-bound, indicating inefficiency rather than logic errors. Against Claude Opus 4, SwiftSolve improves run-level success (73.1% vs 52.6%) at approximately 2x runtime overhead (12.4 s vs 6.8 s). Beyond correctness (pass@k), we report efficiency metrics (eff@k for runtime and memory, incidence of TLE or MLE, and complexity fit accuracy on BigO), demonstrating that profiling and complexity-guided replanning reduce inefficiency while preserving accuracy.

We introduce the Agent GPA (Goal-Plan-Action) framework: an evaluation paradigm based on an agent's operational loop of setting goals, devising plans, and executing actions. The framework includes five evaluation metrics: Goal Fulfillment, Logical Consistency, Execution Efficiency, Plan Quality, and Plan Adherence. Logical Consistency checks that an agent's actions are consistent with its prior actions. Execution Efficiency checks whether the agent executes in the most efficient way to achieve its goal. Plan Quality checks whether an agent's plans are aligned with its goals; Plan Adherence checks if an agent's actions are aligned with its plan; and Goal Fulfillment checks that agent's final outcomes match the stated goals. Our experimental results on two benchmark datasets - the public TRAIL/GAIA dataset and an internal dataset for a production-grade data agent - show that this framework (a) provides a systematic way to cover a broad range of agent failures, including all agent errors on the TRAIL/GAIA benchmark dataset; (b) supports LLM-judges that exhibit strong agreement with human annotation, covering 80% to over 95% errors; and (c) localizes errors with 86% agreement to enable targeted improvement of agent performance.

We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation stack we catalogue recurrent modalities including flip-flop, plan churn, perseveration loops, paralysis and hypervigilance, futile search, belief incoherence, tie break thrashing, corridor thrashing, optimality compulsion, metric mismatch, policy oscillation, and limited-visibility variants. For each we give lightweight online detectors and reusable escape policies (short commitments, a margin to switch, smoothing, principled arbitration). We then show that durable phobic avoidance can persist even under full visibility when learned aversive costs dominate local choice, producing long detours despite globally safe routes. Using First/Second/Third Law as engineering shorthand for safety latency, command compliance, and resource efficiency, we argue that local fixes are insufficient; global failures can remain. To surface them, we propose genetic-programming based destructive testing that evolves worlds and perturbations to maximize law pressure and neurosis scores, yielding adversarial curricula and counterfactual traces that expose where architectural revision, not merely symptom-level patches, is required.

In the supplementary, we first discuss the experimental details and hyperparameters in Section A. Section B, and further present the visualization in RLBench in Section C. Finally, we discuss how to MLP with 512 hidden units and Mish activations. The probability ϵ of random actions is set to 0. 03 in Stochastic Environments. So the sampled trajectories still lead to the collision. Figure 1 illustrates a problematic sampled trajectory after execution. We further evaluate the performance with different replanning steps in Table 1.

Given a previously generated plan, how do we effectively regenerate a new plan?

Robots manipulating in changing environments must act on percepts that are late, noisy, or stale. We present U-LAG, a mid-execution goal-retargeting layer that leaves the low-level controller unchanged while re-aiming task goals (pre-contact, contact, post) as new observations arrive. Unlike motion retargeting or generic visual servoing, U-LAG treats in-flight goal re-aiming as a first-class, pluggable module between perception and control. Our main technical contribution is UAR-PF, an uncertainty-aware retargeter that maintains a distribution over object pose under sensing lag and selects goals that maximize expected progress. We instantiate a reproducible Shift x Lag stress test in PyBullet/PandaGym for pick, push, stacking, and peg insertion, where the object undergoes abrupt in-plane shifts while synthetic perception lag is injected during approach. Across 0-10 cm shifts and 0-400 ms lags, UAR-PF and ICP degrade gracefully relative to a no-retarget baseline, achieving higher success with modest end-effector travel and fewer aborts; simple operational safeguards further improve stability. Contributions: (1) UAR-PF for lag-adaptive, uncertainty-aware goal retargeting; (2) a pluggable retargeting interface; and (3) a reproducible Shift x Lag benchmark with evaluation on pick, push, stacking, and peg insertion.

T able 1: Robustness to model mismatch. Top-1 accuracy of SIPS at the third time quartile (Q3), evaluated on data generated by humans, RL agents, and mismatched models. We ran SIPS assuming r =2, q =0.95, T =10, and a Manhattan ( h Matched parameters are starred (*). We thank the reviewers for engaging carefully with our paper, and for providing helpful and constructive feedback. We will expand on these experiments in the final paper with more domains and cross-method comparisons.