Research Papers

arXiv:2606.01314v1 Announce Type: new Abstract: Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution frameworks typically assume a fixed tool layer and evaluate each skill independently, limiting their ability to repair tool-level failures or reason about interactions among skills. We propose SkillSmith, a synergy-aware skill-tool co-evolution framework. SkillSmith introduces a unified proposal space in which reflection produces atomic bundles that jointly modify skills and tools, allowing tools to be wrapped, edited, composed, split, or retired when skill evolution identifies a reusable capability gap. To guide this joint search, SkillSmith maintains an ecological utility model inspired by Lotka-Volterra dynamics, where an interaction matrix estimated from execution traces captures pairwise complementarity and conflict among skills and provides pressure signals for retrieval, mutation priori

arXiv:2606.01316v1 Announce Type: new Abstract: Scientific discovery demands intelligence, perseverance, and serendipity across vast search spaces. Today, top scientific capabilities remain siloed--one AI system for biological analysis, another for clinical reasoning, mathematical derivation, or materials simulation--and no pre-designed team can anticipate every skill a question will need. Science Earth is a planet-scale scientific runtime in which any capability--a simulation cluster, a wet-lab robot, a proof engine, a single-cell pipeline--can connect to any other, with collaboration structure emerging from the question itself. Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards without prior knowledge of who will meet whom. This shifts the organizing challenge from workflow design to open-ended connectivity. Two runs validate this under structurally distinct conditions. In a trans-Pac

arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration topology remains a critical point of fragility. To analyze this, we propose a Mean-Field Entropy Dynamics framework, modeling the orchestration process as a system governed by the competing forces of task resolution and cumulative context loading. To facilitate validation, we introduce Inverse Workflow Generation (IWG), a multi-agent pipeline that synthesizes process-verifiable, high-complexity benchmarks with dense intermediate checkpoints. We demonstrate that our entropy dynamics model fits empirical trajectories, providing physically interpretable parameters that quantify system stability and performance collapse. Crucially, our analysis uncovers a ``Reasoning Trap": while reasoning-heavy models excel in isolated tasks, they frequently fail as orchestrators due to context squeezing. Eluci

arXiv:2606.01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before producing an answer. When a run fails, final-answer evaluation reveals the endpoint but usually not the point at which the trajectory stopped making recoverable progress. This paper introduces a failure-aware observability framework for diagnosing wasted computation in multi-agent LLM traces. The framework maps recurring failure modes to online trace signals, including tool reliability, execution recovery, orchestration loops, evidence availability, information change, and budget pressure. We instantiate the framework in a three- agent question-answering system and evaluate it on 165 GAIA validation traces under identical execution caps. Operational failures remain common: 22/53 level-1 runs, 33/86 level-2 runs, and 12/26 level-3 runs fail to produce a usable final answer. The traces expose diffe

arXiv:2606.01386v1 Announce Type: new Abstract: We present GuidaPA, a privacy-preserving chatbot for the Italian Public Administration (PA) trained via Federated Learning (FL) on documentation from two national PA platforms, SIGESON and SIDFORS. Our corpus includes approximately 8 pages of SIGESON manuals and 31 pages of SIDFORS manuals/FAQs; while this study uses public documentation as a safe proxy, the intended deployment extends to restricted internal sources (e.g., tickets, officer manuals, database extracts) that can not be centrally pooled due to regulatory and organizational constraints. GuidaPA integrates role-based access control, secure client-side preprocessing, explicit monitoring of non-IID effects, and parameter-efficient federated fine-tuning of large language models. Using QLoRA (4-bit) over 15 federated rounds with an 80/20 train-test split per client, we evaluate answer quality with ROUGE, BLEU-4, and METEOR. The best federated model achieves ROUGE-1/2/L of 61.10/55.

arXiv:2606.01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery. In these systems, failures arise not only from model errors, but also from orchestration-level issues such as tool timeouts, malformed arguments, stale context, contradictory evidence, retry loops, and unverified intermediate outputs. This paper presents a self-healing agentic orchestrator that treats reliability as a bounded runtime control problem. The orchestrator maps observable failure signals to inferred failure classes, selects targeted recovery actions under explicit budgets, verifies recovered trajectories, and records observability traces. We evaluate the approach on a 100-task controlled fault-injection benchmark against static workflow, retry-only, ReAct-style, and full-replanning baselines. Self-healing achieves 98.8\% task success, compared with 94.5\% for retry

arXiv:2606.01417v1 Announce Type: new Abstract: Turkey's e-Government Gateway (e-Devlet) serves over 68 million registered users with more than 9,200 government services, and is increasingly integrating artificial intelligence into citizen-facing applications such as chatbot assistants and eligibility assessments. However, no structured technical governance infrastructure currently connects high-level AI policy frameworks, such as the EU AI Act, OECD AI Principles, and Turkey's own National AI Strategy, to the operational reality of deploying AI within a centralized e-government platform. We propose GovAI-Pipe, a four-layer governance pipeline designed using Design Science Research methodology that maps the AI model lifecycle to governance checkpoints: (1) pre-deployment validation for bias testing, explainability, and privacy impact assessment; (2) deployment governance for risk-tier classification and approval workflows; (3) runtime monitoring for drift detection, fairness tracking,

arXiv:2606.01435v1 Announce Type: new Abstract: LLM-based memory systems increasingly maintain facts that evolve over time, where a recurring failure is conflict resolution: when a fact has multiple contradictory values, which should the agent return? MemoryAgentBench (MAB; Hu et al., 2026) makes this explicit in its FactConsolidation task: facts are numbered, the counterfactual has the higher serial, and agents are told newer facts have larger serials. Yet every published system underperforms: HippoRAG-v2 reaches 54% on single-hop (FC-SH), BM25 48%, Mem0 18%, and the temporal KG Zep/Graphiti just 7%. Multi-hop is near-unsolved (at most 7% across 22 systems). We argue the bottleneck is the assembly step: baselines leave conflict resolution to LLM-mediated retrieval or generation rather than version-aware aggregation. A matched-setup comparison (same backbone, retrieval, chunking, TOP_K) shows that replacing the LLM-judgment answer pipeline with candidate-extraction plus Python max(seri

arXiv:2606.01444v1 Announce Type: new Abstract: Scientific discovery is not only answer generation but revision of the representational regime in which evidence, artifacts, operations, and verifiers are typed. We develop a category-theoretic account of agentic discovery for materials science. In a fixed regime b with schema category S_b, the system state is a copresheaf I_t: S_b -> Set, and provenance is the category of elements \int_{S_b} I_t. Fixed-regime operation is an update on such states, endofunctorial only when provenance-preserving refinements are specified and preserved. Discovery is instead a verified regime transition u: S_b -> S_b': old artifacts are preserved, transported by the left Kan extension Lan_u I_t, and compared with the post-transition state to identify residual content beyond functorial transport. This separates retrieval, search, and discovery without subjective novelty. We instantiate the framework in two systems. In Builder/Breaker, a protein-mechanics worl

arXiv:2606.01457v1 Announce Type: new Abstract: Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money. In its standard form, it treats the variables we control as plain inputs to a black box and cannot tell apart mere correlation from a real cause and effect. Causal Bayesian optimization closes part of this gap by using a known causal graph together with observational data to decide which variables are worth intervening on. Existing methods, however, learn the effect of each possible intervention almost in isolation, even though in a causal system these effects usually share the same underlying mechanisms. We propose graph-coupled causal Bayesian optimization, which ties the different intervention effects together through the uncertainty we have about a small set of shared causal parameters. The result is a causal kernel that lets evidence collected from one intervention improve our estimate of rela

arXiv:2606.01462v1 Announce Type: new Abstract: Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch. In contrast, large reasoning models (LRMs) are trained to excel at producing long chains of reasoning to solve complex problems. How then do LRMs perform at evaluating reasons? We investigate this with the Valid-Answer-Invalid-Reasoning (VAIR) dataset: math problems and solutions with trivial reasoning flaws but valid answers, designed to isolate reasoning evaluation from the confound of reasoning production. Unlike humans, who we find are only 6% worse at grading than solving such problems, we find a substantial production-evaluation gap in LRMs: frontier models score as low as 48% when evaluating VAIR solutions, despite near-perfect solution production. Why this enigma? Through chain-of-thought (CoT) analysis, we find evidence of an answer confirmation bias: LRMs often produce then check for the correct answer

arXiv:2606.01473v1 Announce Type: new Abstract: This paper presents a minimalist brain-computer Musical Interface (BCMI) that functions as a real-time affective sonification system, translating prefrontal EEG activity into adaptive music. Emotional valence is estimated from frontal alpha asymmetry (AF7/AF8) and mapped to musical features such as mode, tempo, rhythmic density, and pitch register through a stochastic generative algorithm. The system integrates wireless EEG acquisition, real-time Python signal processing, and Ableton Live-based music generation synchronized via Lab Streaming Layer. An experiment with 22 participants investigated whether intentional emotional self-induction could modulate the BCMI neurofeedback signal. Linear mixed-effects analyses found no significant effects of target emotion or time, indicating that the frontal alpha asymmetry signal did not reliably distinguish instructed emotional states. Individual differences, including musical training and acting e

arXiv:2606.01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book. The ingredients for doing so within any one domain already exist and are individually validated: masked-latent prediction, action-conditioned latent world models, discrete action tokenization, and joint-embedding prediction on voxelized state. What is not established, and what TERRA addresses, is the transfer question: when does a representation or predictor learned in one structured-state domain carry over to a structurally analogous but otherwise unrelated domain, and by how much. We give this question a formal treatment. We model each domain as a controlled Markov process on a graded latent grid, factor any instantiation into thin domain adapters and a shared domain-invariant core, and identify a cross-domain correspondence with an approximate Markov decision pr

arXiv:2606.01552v1 Announce Type: new Abstract: Role-playing agents(RPAs) are widely used to steer large language models(LLMs) toward role-consistent behavior, yet existing benchmarks mainly evaluate surface-level fidelity and offer limited insight into decision making under role-alignment value conflicts. To address this gap, we introduce RoleCDE, the first benchmark designed to evaluate RPAs under structured conflicts between role-specific values and alignment-oriented constraints. RoleCDE formulates role-aware decision making as cognitive dilemma scenarios, jointly evaluating role-scenario grounding, value conflict resolution, and decision tendencies. The benchmark is constructed at scale, covering approximately 8k diverse role profiles and scenarios and nearly 24k dilemma instances across three difficulty levels and eight role categories. Evaluation of several mainstream LLMs reveals a "Role Value Decoupling" phenomenon, where agents systematically default to alignment-and morality

arXiv:2606.00552v2 Announce Type: replace-cross Abstract: Multi-robot systems (MRS) increasingly offload compute-intensive perception tasks to edge nodes to meet strict time-sensitive Quality-of-Service (QoS) constraints. However, static task orchestration on a shared edge node can severely degrade QoS due to network latency, jitter, and edge-resource contention. We present a pilot edge-centric MRS testbed using Raspberry Pi nodes to evaluate a camera-to-manipulator pipeline under three modes: local execution, static offloading, and a QoS-aware Adaptive Task Placement (ATP) controller. ATP scores candidate placements using a multi-metric cost (normalized latency, CPU utilization, and switching overhead) over two-second control windows. The closed-loop visual servoing testbed is instrumented with sub-millisecond clock synchronization, network emulation, and detailed monitoring of multiple metrics across nodes to capture realistic jitter. Experimental results under compute-stress and net