More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding

• URL: http://arxiv.org/abs/2605.05716v1
• Date: Thu, 07 May 2026 06:01:43 GMT
• Title: More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
• Abstract summary: LLM agent systems are built by stacking components (planning, tools, memory, self-reflection, retrieval)<n>We run a full factorial experiment over all 25=32 subsets of five components on HotpotQA and GSM8K with Llama-3.1-8B/70B conditions.<n>The All-In system is consistently suboptimal: on HotpotQA, a single-tool agent surpasses All-In by 32% (F1 0.233 vs 0.177, p23)<n>Our findings suggest maximally-equipped agent should be replaced by subset selection via interaction-aware analysis.
• Score: 4.738949927143789
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agent systems are built by stacking scaffolding components (planning, tools, memory, self-reflection, retrieval) assuming more is better. We study cross-component interference (CCI): degradation when components interact destructively. We run a full factorial experiment over all 2^5=32 subsets of five components on HotpotQA and GSM8K with Llama-3.1-8B/70B (96 conditions, up to 10 seeds). The All-In system is consistently suboptimal: on HotpotQA, a single-tool agent surpasses All-In by 32% (F1 0.233 vs 0.177, p=0.023); on GSM8K, a 3-component subset beats All-In by 79% (0.43 vs 0.24, p=0.010). Optimal component count is task-dependent (k*=1-4) and scale-sensitive: at 70B, combinations that hurt at 8B provide gains, though All-In still trails the best subset. We fit a main-effects regression (R^2=0.916, adj-R^2=0.899, LOOCV=0.872), compute exact Shapley values, and find 183/325 submodularity violations (56.3%), showing greedy selection is unreliable. A three-body synergy among Tool Use, Self-Reflection, and Retrieval (INT_3=+0.175, 95% CI [+0.003,+0.351]) is reported as exploratory. CCI replicates across model families (Qwen2.5) and is robust to prompt paraphrasing. Our findings suggest maximally-equipped agent defaults should be replaced by task-specific subset selection via interaction-aware analysis.

Related papers

• Beyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation [0.0]
  We investigate how much useful semantic information is lost when heterogeneous sources are collapsed to a single class before they can interact.<n>We find that most information is recovered by retaining a compact set of plausible alternatives.<n>The contribution is a controlled diagnosis of premature semantic collapse as a repeatable information bottleneck in heterogeneous frozen-model composition.
  arXiv  Detail & Related papers  (2026-09-10T18:25:53Z)
• Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study [48.83701310501069]
  This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models.<n>We conduct a systematic empirical study of all $3 times 6 = 18$ combinations of six classifiers paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets.<n>Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across
  arXiv  Detail & Related papers  (2026-06-18T20:51:42Z)
• Operadic consistency: a label-free signal for compositional reasoning failures in LLMs [11.547457355495903]
  We instantiate this idea as operadic consistency (OC) a per-question signal.<n>OC is strongly correlated with accuracy on every dataset.<n>On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction point-estimate lift.
  arXiv  Detail & Related papers  (2026-06-11T17:50:40Z)
• Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI [0.0]
  We ask whether structural properties of intermediate grid states predict whether a symbolic ARC-AGI solver will succeed, framed as a test of conditional mutual information I(X;Ytask) > 0.<n>Across 44,800 runs spanning two architecturally distinct search and DFS solvers, we find most content lies along a single grid-complexity axis.<n>The signal is not explained by solver capacity (-residualized AUC = 0.927 and 0.896 for beam search and SDFS, p 95) and is only weakly coupled to score trajectories (R2 approximately 0)
  arXiv  Detail & Related papers  (2026-06-08T04:51:24Z)
• Agent Explorative Policy Optimization for Multimodal Agentic Reasoning [97.64835302176056]
  Agentic reasoning interleaves two behaviors with a structural asymmetry: thinking and tool use.<n>Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training.<n>We propose AXPO (Agent eXplorative Policy Optimization) for each all-wrong tool-using subgroup.
  arXiv  Detail & Related papers  (2026-05-27T17:36:39Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems [0.0]
  Compound AI systems route tasks through hierarchies of specialised components.<n>We introduce BOHM, which extracts a hierarchical attribution tree directly from the routing weights such systems already maintain.<n>BOHM satisfies efficiency, monotonicity, symmetry, and weak suppression but not Shapley's additivity.
  arXiv  Detail & Related papers  (2026-05-19T19:38:14Z)
• ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems [51.56484100374058]
  On LongMemEval-500, ZenBrain matches a long-context oracle's binary-judge accuracy to within 4.5 pp.<n> ZenBrain is a 7-layer neuroscience-inspired memory architecture.
  arXiv  Detail & Related papers  (2026-04-26T20:39:19Z)
• vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents [0.0]
  We present **vstash**, a local-first document memory system that combines vector similarity search with fulltext keyword matching.<n>All data resides in a single file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching.
  arXiv  Detail & Related papers  (2026-04-16T19:22:58Z)
• THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture [0.0]
  THEIA is a 2.75M modular neural architecture that learns the complete Kleene three-valued logic (K3) truth table from task data without external symbolic inference or hand-encoded K3 gate primitives.<n> Transformer baselines also reach >99% on all 39 rules, and flats match THEIA on Phase-1 accuracy within 0.04pp.
  arXiv  Detail & Related papers  (2026-04-13T10:44:15Z)
• PRISM: Differentiable Analysis-by-Synthesis for Fixel Recovery in Diffusion MRI [1.3063136334195184]
  This work introduces, a differentiable analysis-by-synthesis framework that fits an explicit multi-compartment forward model end-to-end cerebrospinal model.<n> PRISM supports fast MSE objective and a Rician negative log-ze-likelihood (NLL) that jointly learns without information.<n> PRISM achieves 3.5 degrees best-match angular error with 95% recall is 1.9x lower than best baseline.
  arXiv  Detail & Related papers  (2026-03-31T21:22:49Z)
• Greedy Is a Strong Default: Agents as Iterative Optimizers [0.22843885788439797]
  We replace the random proposal generator with an LLM agent that reasons about evaluation diagnostics to propose informed candidates.<n>We evaluate on four tasks spanning discrete, mixed, and continuous search spaces.
  arXiv  Detail & Related papers  (2026-03-28T21:26:40Z)
• Label-Free Cross-Task LoRA Merging with Null-Space Compression [50.63908869296697]
  We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry.<n>NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks.
  arXiv  Detail & Related papers  (2026-03-27T11:34:41Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• 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)
• Impact of Labeling Inaccuracy and Image Noise on Tooth Segmentation in Panoramic Radiographs using Federated, Centralized and Local Learning [46.232038247686745]
  Federated learning (FL) may mitigate privacy constraints, heterogeneous data quality, and inconsistent labeling in dental diagnostic AI.<n>We compared FL with centralized (CL) and local learning (LL) for tooth segmentation in panoramic radiographs across multiple data corruption scenarios.
  arXiv  Detail & Related papers  (2025-09-08T11:07:47Z)
• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation [91.12575065731883]
  We propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS) The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted $ell_n$-norm loss and IoU-based loss. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR.
  arXiv  Detail & Related papers  (2020-05-07T16:00:27Z)

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.