arXiv subjects

Yuma Ichikawa

Publications and source records attributed to Yuma Ichikawa.

At least 19 recordsLinked to original sources

arXiv2026

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse. We present Kozuchi Agent, a language-agnostic open-weight repair agent and CI-operated evaluation pipeline. Explicit phases, persistent state, deterministic tools, a model-independent action interface, and cross-agent test-time selection make runs auditable and repeatable. With locally hosted Qwen3.5-27B, no fine-tuning, and TTS@8, Kozuchi resolves 374/500 SWE-bench Verified instances on the official evaluator. Unchanged on Multi-SWE-bench Java, the same 27-billion-parameter agent resolves 41/128 instances (32.03%), ranking first among strict open-weight submissions and fourth of 42 overall; on Python it ranks 12th of 135 and first among open-weight systems. Per-phase behavior remains within +/-5 percentage points across languages. Remaining failures mainly reflect semantic correctness, Java-specific harness issues, and selection errors. Across both tracks, results compare favorably with open/local peers by parameter count. Analysis of candidate diversity, selector regret, and patch reliability shows that the remaining gap is primarily semantic correctness and selection rather than edit formatting or proprietary-model access. Operationally, reusable CI stages reduce operator touch-points from five to one across heterogeneous internal clusters.

cs.SE↗

arXiv2026

From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization

Compressing large language models to two bits or fewer is increasingly feasible through block-wise post-training quantization; cross-block variants reconstruct neighboring Transformer blocks within a moving window. In the fixed two-block setting studied here, the matched sequential baseline moves this window through the network once, so errors introduced early in the sweep are not revisited. We propose Interleaved Cross-Block Quantization (ICBQ), a scheduling modification that revisits the boundary pair between consecutive chunks. Each seam pair is refined twice: first at the end of one chunk and again at the start of the next. The method retains the local two-block objective and reuses the calibration inputs of existing block-wise PTQ pipelines. Under stated local contraction and smoothness assumptions, we derive a depth-wise upper-bound comparison in which seam revisits multiply the propagated term while the residual remains bounded independently of depth. In the reported experiments, ICBQ reduces ternary-quantization perplexity relative to the matched Sequential CBQ baseline, yields finite perplexity in configurations where the baseline has severe degradation, and can also be used with 3-bit and 2-bit GPTQ.

cs.AI↗

arXiv2026

One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization

One-bit post-training quantization represents each weight using only its sign, requiring all deployment contexts to share the same binary weight matrix even when their activation statistics favor different sign patterns. We study this shared-sign constraint and introduce Quantum Random Access Quantization (QRAQ). This framework encodes context-dependent signs in a quantum random-access code and retrieves them via context-matched Pauli measurements. Under an explicit fresh-copy logical readout model, QRAQ produces an unbiased, context-specific binary surrogate with a tractable shot-noise penalty. We prove a row-wise separation from shared-sign one-bit PTQ with signed per-row scales. When the optimal context-wise signs are incompatible, QRAQ achieves a strictly lower ideal reconstruction risk. We also derive finite-shot and calibrated-noise conditions under which this separation is retained. Fixed-readout quantum schemes are classically simulable, so the relevant resource in this model is measurement incompatibility rather than quantization alone. Finally, we characterize the role of scale granularity, provide finite-sample certificates, and evaluate the predicted ideal, finite-shot, noisy, and multi-context regimes in simulator experiments.

quant-ph↗

arXiv2026

Addressable Recall Compaction for Long Context-Window Control in AI Agents

Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window. Existing compaction methods address this limitation by discarding, summarizing, or retrieving earlier information, but they may remove task-critical details or fail to recover them reliably. We propose ARC (Addressable Recall Compaction), a context-management framework that separates archival storage from active-context presentation. ARC stores tool observations in an append-only, ID-addressable log and replaces older observations with compact citations when compaction is required. The agent can subsequently use these identifiers to request stored content without re-executing the corresponding tools or depending solely on similarity-based retrieval. We evaluate ARC using Qwen3-8B with a 16k context window and Qwen3-32B with a 32k context window. On the Needle-in-a-Haystack evaluation, ARC achieves an average exact-answer accuracy of 99.40%, compared with 88.12% for the best-performing baseline in our evaluation. ARC also reduces estimated serving time and HBM traffic under our hardware-cost model. On the LongBench-v2 Hard subset, ARC obtains an average accuracy of 29.97%, compared with 28.25% for the best-performing baseline. These results indicate that explicit, address-based recall can improve information retention and serving efficiency relative to the evaluated context-management baselines under the tested settings.

cs.AI↗

arXiv2026

LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans

AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior. The defining question for deployment is no longer merely what agents can do, but who controls what they are allowed to become. We introduce logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them. logos compiles heterogeneous multimodal inputs, including documents, images, audio, tables, databases, APIs, and human instructions into versioned agent packs containing agents, tools, knowledge, tests, permissions, and policies. During operation, it transforms agent activity into portable, auditable event traces and applies fail-closed verification across frameworks and backends. Every learned prompt, memory, skill, tool, role, or workflow remains an untrusted release candidate until held-out execution evidence, human-controlled policy, and explicit authorization permit its promotion. This architecture enables "verifiable human-agent loop engineering": agents can act, ask, learn, and propose improvements, while humans can steer objectives, permissions, approvals, and irreversible actions without interrupting continuous operation. logos provides a living logic for accountable automation. Agents may evolve at machine speed, but only evidence and human authority can close the loop.

cs.AI↗

arXiv2026

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning

On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter-mode setting, however, the adapter is more than a compact storage module; it introduces an additional dense floating-point branch, maintains a trainable state for local updates, and acts as a unit of communication and hot-swapping.We introduce LoRDBA, a LoRA-compatible adapter that replaces both low-rank factors with binary sign carriers while representing magnitudes through lightweight, channel-wise scales, converting the dense adapter branch into two sign-accumulation matrix multiplications interleaved with channel-wise scaling. A finite-sample analysis shows that reconstruction quality is governed by the residual-to-magnitude ratio of the original LoRA factors. In adapter-mode experiments, LoRDBA outperforms low-bit baselines at matched model sizes while matching fp16 LoRA quality in selected regimes. The unmerged adapter incurs at most 8% prefill latency overhead at matched rank r=16 despite an over 10x reduction in adapter footprint, with moderate training memory overhead of approximately 1.6x that of fp16 LoRA.

cs.LG↗

arXiv2026

EVE-Agent: Evidence-Verifiable Self-Evolving Agents

Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human annotations. Yet, without verifiable evidence, this loop can reward fluent but unsupported examples, turning the self-generated curriculum into an opaque and potentially unreliable training signal. We argue that evidence verifiability is a prerequisite for trustworthy self-evolution in search agents: each generated instance should include not only an answer but also a source-grounded span whose contribution to that answer can be measured. We introduce EVE-Agent, an Evidence-Verifiable Self-Evolving Agent that operationalizes this principle through a modification to the proposer--solver framework. The proposer generates a question, an answer, and a verbatim evidence span. An evidence verifier then rewards the span according to the marginal accuracy gain when the evidence is provided. This produces a training signal that favors evidence that genuinely helps answer the question, without requiring oracle answers, human labels, or external annotations. EVE-Agent leaves the backbone model, retriever, search tool, and optimization framework unchanged. Experiments show that EVE-Agent substantially improves evidence-grounded correctness over prior self-evolving search agents. The resulting curriculum is not merely self-generated but auditable by construction: each training example carries an inspectable source span that explains why it should be trusted.

cs.AI↗

arXiv2026

Tensor-Network Population Annealing

We propose a hybrid sampling method, tensor-network population annealing (TNPA), which combines tensor-network (TN) initialization with population annealing (PA). We apply this method to the two-dimensional Edwards-Anderson Ising spin glass. The approach is motivated by the limitations of existing methods: TN-based samplers can become numerically unstable in frustrated spin systems at low temperatures, whereas conventional PA requires a long annealing schedule when started from the high-temperature limit. In TNPA, TN contractions are used only within a reliable temperature range to generate initial configurations that are close to the equilibrium distribution. The subsequent low-temperature equilibration is then carried out by PA. To stabilize the initialization process, we introduce a diagnostic based on the effective sample size that adaptively selects the initialization temperature. The proposed framework provides a practical and physically motivated route to low-temperature sampling by combining the complementary strengths of TN and PA.

cond-mat.stat-mech↗

arXiv2026

OneComp: One-Line Revolution for Generative AI Model Compression

Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading performance; however, its practical implementation remains challenging as practitioners navigate a fragmented landscape of quantization algorithms, precision budgets, data-driven calibration strategies, and hardware-dependent execution regimes. We present OneComp, an open-source compression framework that transforms this expert workflow into a reproducible, resource-adaptive pipeline. Given a model identifier and available hardware, OneComp automatically inspects the model, plans mixed-precision assignments, and executes progressive quantization stages, ranging from layer-wise compression to block-wise refinement and global refinement. A key architectural choice is treating the first quantized checkpoint as a deployable pivot, ensuring that each subsequent stage improves the same model and that quality increases as more compute is invested. By converting state-of-the-art compression research into an extensible, open-source, hardware-aware pipeline, OneComp bridges the gap between algorithmic innovation and production-grade model deployment.

cs.LG↗

arXiv2026

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression

Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-cost bottleneck. Across Transformers, CNNs, and MLPs, learned sign matrices resist low-rank approximation and are spectrally indistinguishable from an i.i.d. Rademacher baseline. This randomness gives rise to the lower bound of sub-bit model compression -- the one-bit wall. Despite this apparent randomness, most weights retain their initialization signs; flips primarily occur via rare near-zero boundary crossings, suggesting that sign-pattern randomness is largely inherited from initialization. We formalize this behavior with sign lock-in theory, a stopping-time analysis of sign flips under SGD noise. Under bounded updates and a rare re-entry condition into a small neighborhood of zero, the number of effective sign flips exhibits a geometric tail. Building on this mechanism, we introduce a from-scratch low-rank sign-template training method that prevents the emergence of this one-bit wall.

cs.LG↗

arXiv2026

Thermal Min-Max Games: Unifying Bounded Rationality and Typical-Case Equilibrium

Strategic-form min-max game theory examines the existence, multiplicity, selection of equilibria, and the worst-case computational complexity under perfect rationality. However, in many applications, games are drawn from an ensemble, and players exhibit bounded rationality. We introduce thermal min-max games, a thermodynamic relaxation that unifies bounded and perfect rationality by assigning each player a temperature to regulate their rationality level. To analyze typical behavior in the large-strategy limit, we develop a nested replica framework for this relaxation. This theory provides tractable predictions for typical equilibrium values and mixed-strategy statistics as functions of rationality strength, strategy-count aspect ratio, and payoff randomness. Numerical experiments demonstrate that these asymptotic predictions accurately align with the equilibrium of finite games of moderate size.

cs.GT↗

arXiv2025

More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization

For extreme low-bit quantization of large language models (LLMs), Double Binary Factorization (DBF) is attractive as it enables efficient inference without sacrificing accuracy. However, the scaling parameters of DBF are too restrictive; after factoring out signs, all rank components share the same magnitude profile, resulting in performance saturation. We propose Multi-envelope DBF (MDBF), which retains a shared pair of 1-bit sign bases but replaces the single envelope with a rank-$l$ envelope. By sharing sign matrices among envelope components, MDBF effectively maintains a binary carrier and utilizes the limited memory budget for magnitude expressiveness. We also introduce a closed-form initialization and an alternating refinement method to optimize MDBF. Across the LLaMA and Qwen families, MDBF enhances perplexity and zero-shot accuracy over previous binary formats at matched bits per weight while preserving the same deployment-friendly inference primitive.

cs.LG↗

arXiv2025

PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation

Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases prefill latency and makes long-context decoding more memory-bound, as KV-cache reads and writes dominate inference time over arithmetic operations. We propose Parallel Hierarchical Operation for TOp-down Networks (PHOTON), a hierarchical autoregressive model that replaces horizontal scanning with vertical, multi-resolution context scanning. PHOTON maintains a hierarchy of latent streams: a bottom-up encoder compresses tokens into low-rate contextual states, while lightweight top-down decoders reconstruct fine-grained token representations in parallel. We further introduce recursive generation that updates only the coarsest latent stream and eliminates bottom-up re-encoding. Experimental results show that PHOTON is superior to competitive Transformer-based language models regarding the throughput-quality trade-off, providing advantages in long-context and multi-query tasks. In particular, this reduces decode-time KV-cache traffic, yielding up to $10^{3}\times$ higher throughput per unit memory.

cs.LG↗

arXiv2025

LPCD: Unified Framework from Layer-Wise to Submodule Quantization

Post-training quantization (PTQ) aims to preserve model-level behavior; however, most methods focus on individual linear layers. Even recent extensions, such as QEP and LoaQ, which mitigate error propagation or target specific submodules, still rely on layer-wise formulations and fail to capture the behavior of larger submodules. We introduce Layer-Projected Coordinate Descent (LPCD), a unified framework that extends PTQ beyond layers by optimizing relaxed objectives across arbitrary submodules and projecting the solutions with layer-wise quantizers. LPCD generalizes existing methods and provides a principled approach to quantizing complex submodules while maintaining the efficiency and compatibility of layer-wise PTQ pipelines. Across diverse LLM architectures and bit-widths, LPCD-based submodule quantization consistently enhances both layer-wise PTQ methods and existing submodule approaches.

stat.ML↗

arXiv2025

High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator

Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused on the properties of surrogate gradients and their convergence, the influence of quantization hyperparameters, such as bit width and quantization range, on learning dynamics remains largely unexplored. We theoretically show that in the high-dimensional limit, STE dynamics converge to a deterministic ordinary differential equation. This reveals that STE training exhibits a plateau followed by a sharp drop in generalization error, with plateau length depending on the quantization range. A fixed-point analysis quantifies the asymptotic deviation from the unquantized linear model. We also extend analytical techniques for stochastic gradient descent to nonlinear transformations of weights and inputs.

stat.ML↗

arXiv2025

Continuous Parallel Relaxation for Finding Diverse Solutions in Combinatorial Optimization Problems

Finding the optimal solution is often the primary goal in combinatorial optimization (CO). However, real-world applications frequently require diverse solutions rather than a single optimum, particularly in two key scenarios. The first scenario occurs in real-world applications where strictly enforcing every constraint is neither necessary nor desirable. Allowing minor constraint violations can often lead to more cost-effective solutions. This is typically achieved by incorporating the constraints as penalty terms in the objective function, which requires careful tuning of penalty parameters. The second scenario involves cases where CO formulations tend to oversimplify complex real-world factors, such as domain knowledge, implicit trade-offs, or ethical considerations. To address these challenges, generating (i) penalty-diversified solutions by varying penalty intensities and (ii) variation-diversified solutions with distinct structural characteristics provides valuable insights, enabling practitioners to post-select the most suitable solution for their specific needs. However, efficiently discovering these diverse solutions is more challenging than finding a single optimal one. This study introduces Continual Parallel Relaxation Annealing (CPRA), a computationally efficient framework for unsupervised-learning (UL)-based CO solvers that generates diverse solutions within a single training run. CPRA leverages representation learning and parallelization to automatically discover shared representations, substantially accelerating the search for these diverse solutions. Numerical experiments demonstrate that CPRA outperforms existing UL-based solvers in generating these diverse solutions while significantly reducing computational costs.

stat.ML↗

arXiv2025

Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization

Layer-wise PTQ is a promising technique for compressing large language models (LLMs), due to its simplicity and effectiveness without requiring retraining. However, recent progress in this area is saturating, underscoring the need to revisit its core limitations and explore further improvements. We address this challenge by identifying a key limitation of existing layer-wise PTQ methods: the growth of quantization errors across layers significantly degrades performance, particularly in low-bit regimes. To address this fundamental issue, we propose Quantization Error Propagation (QEP), a general, lightweight, and scalable framework that enhances layer-wise PTQ by explicitly propagating quantization errors and compensating for accumulated errors. QEP also offers a tunable propagation mechanism that prevents overfitting and controls computational overhead, enabling the framework to adapt to various architectures and resource budgets. Extensive experiments on several LLMs demonstrate that QEP-enhanced layer-wise PTQ achieves substantially higher accuracy than existing methods. Notably, the gains are most pronounced in the extremely low-bit quantization regime.

cs.LG↗

arXiv2025

High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve

In variational autoencoders (VAEs), the variational posterior often collapses to the prior, known as posterior collapse, which leads to poor representation learning quality. An adjustable hyperparameter beta has been introduced in VAEs to address this issue. This study sharply evaluates the conditions under which the posterior collapse occurs with respect to beta and dataset size by analyzing a minimal VAE in a high-dimensional limit. Additionally, this setting enables the evaluation of the rate-distortion curve of the VAE. Our results show that, unlike typical regularization parameters, VAEs face "inevitable posterior collapse" beyond a certain beta threshold, regardless of dataset size. Moreover, the dataset-size dependence of the derived rate-distortion curve suggests that relatively large datasets are required to achieve a rate-distortion curve with high rates. These findings robustly explain generalization behavior observed in various real datasets with highly non-linear VAEs.

stat.ML↗