Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver $+0.0$pp over no-skill baselines while human-curated ones deliver $+16.2$pp: the bottleneck is not skill authoring but lifecycle management. We introduce \textbf{Ratchet}, a single-agent loop in which a frozen LLM writes, retrieves, curates, and retires its own natural-language skills. Ratchet integrates four candidate hygiene mechanisms: outcome-driven retirement, a bounded active-cap, meta-skill authoring guidance, and pattern canonicalisation. On MBPP+ hard-100 with Claude Opus 4.7, Ratchet lifts held-out pass@1 from a $0.258 \pm 0.047$ baseline to a late-window rolling mean of $0.584$ (peak $0.658 \pm 0.042$) across 100 rounds and 3 seeds, a $+0.328 \pm 0.018$ rolling-mean gain where the no-skill control drifts at $+0.002 \pm 0.005$; the same recipe transfers to an agentic solver on SWE-bench Verified ($+0.22$ peak lift over 20 rounds). Eight ablations (A1--A8) reveal that the minimal working recipe is smaller than our design suggests: retirement and the meta-skill authoring prior are load-bearing, while explicit deduplication (canonicalisation, cover-guard) is subsumed by the meta-skill itself. A non-divergence proposition shows that bounded cap and retirement threshold together prevent expected performance from drifting below the no-skills floor.

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Self-evolving skill libraries face a silent failure mode we term \emph{library drift}: unbounded skill accumulation without outcome-driven lifecycle management causes retrieval degradation, false-positive injections, and performance stagnation. Recent evaluation confirms the symptom--LLM-authored skills deliver +0.0pp gain while human-curated ones deliver +16.2pp (SkillsBench)--yet the underlying mechanism has not been isolated. We provide (1) a reproducible trigger: ablations that isolate drift--one disables skill injection (flat floor, +0.002), one imposes premature retirement (active harm, $-$0.019); (2) trace-level diagnostics: an append-only evidence log with per-skill contribution scores, attribution verdicts, and router engagement metrics that make the failure visible before it reaches end-task scores; and (3) a verified fix: a minimal governance recipe (outcome-driven retirement + bounded active-cap + meta-skill authoring prior) that lifts held-out pass@1 from a 0.258 baseline to a late-window mean of 0.584 (rolling gain $+$0.328) on MBPP+ hard-100 over 100 rounds. Eight ablations decompose which governance mechanisms are load-bearing and which are subsumed, providing a concrete playbook for diagnosing library drift in any self-evolving agent.

Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher to a 2.29B student model. Our approach achieves 8.7x lower inference latency and a 3x reduction in model size while retaining 54-72% of the teacher's performance. The framework utilizes VGGT as the vision encoder and a multi-task distillation pipeline with uncertainty-aware loss weighting. To improve reasoning without chain-of-thought (CoT) data, we introduce "Hidden CoT": learnable latent tokens that serve as an internal scratchpad before answer generation. This is the first use of latent scratchpad reasoning in distilled 3D VLMs. The student model jointly performs spatial description, depth estimation, and object detection. Experiments on ScanNet and 3D-FRONT show strong spatial understanding, reaching 68-72% accuracy on proximity and contact tasks. Our framework enables efficient 3D scene QA on resource-constrained platforms.

Hindsight Preference Optimization for Financial Time Series Advisory

Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management. Training language models for such predictive advisory faces a fundamental challenge: quality depends on outcomes unknown at prediction time. We bridge two ideas from reinforcement learning -- using information unavailable during execution to retrospectively generate training signal, and preference alignment -- and propose Hindsight Preference Optimization: observed outcomes let an LLM judge rank candidate advisories on dimensions that scalar metrics cannot capture, producing preference pairs for DPO without human annotation. We apply this to Vision-Language-Model-based predictive advisories on S&P 500 equity time series, demonstrated by a 4B model outperforming its 235B teacher on both accuracy and advisory quality.

Beyond ZOH: Advanced Discretization Strategies for Vision Mamba

Vision Mamba, as a state space model (SSM), employs a zero-order hold (ZOH) discretization, which assumes that input signals remain constant between sampling instants. This assumption degrades temporal fidelity in dynamic visual environments and constrains the attainable accuracy of modern SSM-based vision models. In this paper, we present a systematic and controlled comparison of six discretization schemes instantiated within the Vision Mamba framework: ZOH, first-order hold (FOH), bilinear/Tustin transform (BIL), polynomial interpolation (POL), higher-order hold (HOH), and the fourth-order Runge-Kutta method (RK4). We evaluate each method on standard visual benchmarks to quantify its influence in image classification, semantic segmentation, and object detection. Our results demonstrate that POL and HOH yield the largest gains in accuracy at the cost of higher training-time computation. In contrast, the BIL provides consistent improvements over ZOH with modest additional overhead, offering the most favorable trade-off between precision and efficiency. These findings elucidate the pivotal role of discretization in SSM-based vision architectures and furnish empirically grounded justification for adopting BIL as the default discretization baseline for state-of-the-art SSM models.

Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems

Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods $\times$ 4 tasks $\times$ 3 repeats), 49% score below zero-shot; on Amazon Nova Lite, the failure rate is even higher. Yet on one task, all six methods improve over zero-shot by up to $+6.8$ points. What distinguishes success from failure? We investigate with 18,000 grid evaluations and 144 optimization runs, testing two assumptions behind end-to-end optimization tools like TextGrad and DSPy: (A) individual prompts are worth optimizing, and (B) agent prompts interact, requiring joint optimization. Interaction effects are never significant ($p > 0.52$, all $F < 1.0$), and optimization helps only when the task has exploitable output structure -- a format the model can produce but does not default to. We provide a two-stage diagnostic: an \$80 ANOVA pre-test for agent coupling, and a 10-minute headroom test that predicts whether optimization is worthwhile -- turning a coin flip into an informed decision.

Do Agent Rules Shape or Distort? Guardrails Beat Guidance in Coding Agents

Developers increasingly guide AI coding agents through natural language instruction files (e.g., CLAUDE.md, .cursorrules), yet no controlled study has measured whether these rules actually improve agent performance or which properties make a rule beneficial. We scrape 679 such files (25,532 rules) from GitHub and conduct the first large-scale empirical evaluation, running over 5,000 agent runs with a state-of-the-art coding agent on SWE-bench Verified. Rules improve performance by 7--14 percentage points, but random rules help as much as expert-curated ones -- suggesting rules work through context priming rather than specific instruction. Negative constraints ("do not refactor unrelated code") are the only individually beneficial rule type, while positive directives ("follow code style") actively hurt -- a pattern we analyze through the lens of potential-based reward shaping (PBRS). Moreover, individual rules are mostly harmful in isolation yet collectively helpful, with no degradation up to 50 rules. These findings expose a hidden reliability risk -- well-intentioned rules routinely degrade agent performance -- and provide a clear principle for safe agent configuration: constrain what agents must not do, rather than prescribing what they should.

From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action with no recourse. We introduce Conformal Social Choice, a post-hoc decision layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding prediction sets with a marginal coverage guarantee: the correct answer is included with probability ${\geq}\,1{-}α$, without assumptions on individual model calibration. A hierarchical action policy maps singleton sets to autonomous action and larger sets to human escalation. On eight MMLU-Pro domains with three agents (Claude Haiku, DeepSeek-R1, Qwen-3 32B), coverage stays within 1--2 points of the target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: 81.9% of wrong-consensus cases are intercepted at $α{=}0.05$. Because the layer refuses to act on cases where debate is confidently wrong, the remaining conformal singletons reach 90.0--96.8% accuracy (up to 22.1pp above consensus stopping) -- a selection effect, not a reasoning improvement. This safety comes at the cost of automation, but the operating point is user-adjustable via $α$.

Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach

Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes. Inspired by the theory of Ricci flow in differential geometry, we theoretically establish that introducing discrete Ricci flow into hypergraph structures can effectively regulate node feature evolution and thereby alleviate over-smoothing. Building on this insight, we propose Ricci Flow-guided Hypergraph Neural Diffusion(RFHND), a novel message passing paradigm for hypergraphs guided by discrete Ricci flow. Specifically, RFHND is based on a PDE system that describes the continuous evolution of node features on hypergraphs and adaptively regulates the rate of information diffusion at the geometric level, preventing feature homogenization and producing high-quality node representations. Experimental results show that RFHND significantly outperforms existing methods across multiple benchmark datasets and demonstrates strong robustness, while also effectively mitigating over-smoothing.

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance.