MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment

• URL: http://arxiv.org/abs/2603.18637v1
• Date: Thu, 19 Mar 2026 09:00:47 GMT
• Title: MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment
• Abstract summary: We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once.<n>We propose MOSAIC, a multi-objective framework for closed-loop data mixture search built on a unified L1-L3 evaluation interface.
• Score: 1.356919241968803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints. We propose MOSAIC (Multi-Objective Slice-Aware Iterative Curation for Alignment), a multi-objective framework for closed-loop data mixture search built on a unified L1-L3 evaluation interface. MOSAIC turns slice-level failure profiles into executable data actions, including dataset-level mixture ratios, bucket-level weights, and focus criteria. Under a fixed 1M-token budget and five rounds of independent fine-tuning from the same base model, MOSAIC improves internal XGuard from 2.76 to 4.67 while keeping OrBench at 4.41 and IFEval at 3.65. The final Pareto solution also generalizes better than a random static LoRA baseline on independent attack, over-refusal, and capability tests, suggesting that structured failure diagnosis can serve as a practical control signal for budgeted data construction. Code is available at https://github.com/douyipu/mosaic.

Related papers

• FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs [24.30721158142313]
  Fragmented safety evaluation undermines the governance of dangerous AI capabilities.<n>We present a modular framework that evaluates each model through three orthogonal pipelines---Knowledge, Defense, and Harm.<n>Our first contribution is a horizontal comparison of dangerous capability across models and model families.<n>The second is a temporal analysis of capability evolution: tracking $K$, $D$, and $H$ against model release dates reveals that dangerous capability has not monotonically declined.
  arXiv  Detail & Related papers  (2026-09-02T06:31:39Z)
• Coverage, Not Credit: Failure-Credit Routing of Zeroth-Order Perturbation Budgets Does Not Improve On-Pool Sample Efficiency for LLM Agents [0.0]
  Trajectory-level credit assignment can localize which module causes failures using only verifiable signals.<n>We ask whether failure credit should route a fixed zeroth-order/evolution-strategies (ZO/ES) perturbation budget.<n>Across a synthetic environment and frozen Qwen2.5-1.5B/3B and SmolLM2-1.7B agents, we find no statistically detectable improvement over uniform allocation in any on-pool comparison.
  arXiv  Detail & Related papers  (2026-08-28T07:27:02Z)
• Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models [63.96252564303143]
  Embodied-R1.5 is a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities.<n>We build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe.<n>With only 8B parameters, Embodied-R1.5 SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4.
  arXiv  Detail & Related papers  (2026-06-09T18:07:50Z)
• Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts [0.07812854697536452]
  We present a large-scale study of multi-tier LLM routing with 206,000 query-model pairs across six benchmarks.<n>We show that a substantial portion of reported unsolvability stems from evaluation artifacts.
  arXiv  Detail & Related papers  (2026-05-08T07:49:24Z)
• PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection [19.162716475205308]
  Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences.<n>A single injection into the Planner's context achieves cascade amplification, corrupting all downstream sub-tasks simultaneously.<n>We introduce PlanFlip, a framework comprising four planning-phase prompt injection attacks.
  arXiv  Detail & Related papers  (2026-04-30T07:22:06Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications [51.56484100374058]
  We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow.<n>The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract.<n>We evaluate the harness on ticket-routing and BEIR tasks with full Azure matrix coverage.
  arXiv  Detail & Related papers  (2026-03-28T18:03:32Z)
• Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track [51.15679610275694]
  We develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance.<n>Our solution achieves a J&F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.
  arXiv  Detail & Related papers  (2026-03-24T23:45:15Z)
• Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection [0.0]
  Budget-Sensitive Discovery Score (BSDS) penalizes false discoveries at each budget level.<n>Discovery Quality Score (DQS) provides a single summary statistic that no proposer can inflate by performing well at a cherry-picked budget.<n> framework applies to any setting where candidates are selected under budget constraints and asymmetric error costs.
  arXiv  Detail & Related papers  (2026-03-12T18:09:53Z)
• Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval [0.0]
  Legal teams increasingly use machine learning to triage large volumes of contractual evidence.<n>Many models are opaque, non-deterministic, and difficult to align with frameworks such as HIPAA or NERC-CIP.<n>We study a simple, reproducible alternative based on deterministic dual encoders and transparent fuzzy triage bands.
  arXiv  Detail & Related papers  (2026-03-08T00:31:34Z)
• Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use [6.622648583261088]
  Agentic language models must plan, call tools, and execute long-horizon actions where a single misstep can cause irreversible harm.<n>We introduce MOSAIC, a framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable.<n>We show that MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance.
  arXiv  Detail & Related papers  (2026-03-03T17:59:35Z)
• Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning [17.384089089363382]
  We identify a root cause that existing methods overlook: the uniform penalization of errors.<n>Current approaches treat all incorrect rollouts within a group identically.<n>We propose the Asymmetric Confidence-aware Error Penalty (ACE)
  arXiv  Detail & Related papers  (2026-02-24T22:46:43Z)
• ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces [3.151184728006369]
  We present ACAR, a measurement framework for studying multi-model orchestration under auditable conditions.<n>ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes.<n>We evaluate ACAR on 1,510 tasks spanning four benchmarks, producing more than 7,550 auditable runs.
  arXiv  Detail & Related papers  (2026-02-06T23:27:17Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Benchmarking the Robustness of LiDAR Semantic Segmentation Models [78.6597530416523]
  In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions. We propose a new benchmark called SemanticKITTI-C, which features 16 out-of-domain LiDAR corruptions in three groups, namely adverse weather, measurement noise and cross-device discrepancy. We design a robust LiDAR segmentation model (RLSeg) which greatly boosts the robustness with simple but effective modifications.
  arXiv  Detail & Related papers  (2023-01-03T06:47:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.