arXiv subjects

Eric Jiang

Publications and source records attributed to Eric Jiang.

5 recordsLinked to original sources

arXiv2026

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

Recent developments in AI for Mathematics (AI4Math), especially Large Language Model (LLM)-driven theorem provers, has achieved remarkable success in formal proof generation for well-defined mathematical problems through Interactive Theorem Proving (ITP) languages. However, current systems remain fundamentally limited in tackling frontier research mathematics, such as discovering new theorems or resolving open conjectures, which are often open-ended, under-specified, and involve multiple layers of abstraction. We argue that the next leap in AI4Math systems requires a decisive shift from predefined problem-solvers to research agents that can address frontier mathematical challenges with rigorous formal mathematical reasoning. In this position paper, we provide a systematic review of the field, covering datasets, auto-formalization, and proof synthesis. More importantly, we identify core limitations of existing systems in serving as mathematical research agents, examining issues across datasets, relational structure, mathematical exploration, tool ecosystem, and human-AI collaboration, outlining a strategic road-map for the future of AI4Math.

cs.CL↗

arXiv2026

RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification

Class imbalance poses a fundamental challenge in risk-sensitive applications such as fraud detection and medical diagnosis, where minority-class samples are scarce yet critical for accurate classification. Existing oversampling methods generate synthetic samples to rebalance class distributions; however, they often produce large numbers of low-quality candidates that distort decision boundaries or introduce artifacts, leading to overfitting and degraded generalization. In this work, we introduce \textbf{RUBRIC}, a generator-agnostic filtering framework that formulates synthetic sample selection as a quality-over-quantity optimization problem. RUBRIC ranks candidates using a realism-utility trade-off: realism is estimated via a neural density-ratio discriminator from each candidate's resemblance to real minority samples, while utility captures proximity to the decision boundary through a concave, margin-based scoring function $g_-(t)=-\log(1+e^{-t/τ})$. The discriminator uses the same architecture and training protocol on every benchmark and is fit independently to that dataset's real minority class versus its synthetic pool. We show that, under mild regularity conditions, the proposed filtering framework monotonically tightens the generalization bound for margin-based classifiers by jointly reducing distribution shift and suppressing near-negative tail contributions. Through extensive experiments on standard public imbalanced-classification benchmarks, we demonstrate that RUBRIC boosts minority-class recall while preserving overall discriminative ability across multiple data generators. Sensitivity analyses in $λ$ and the selection budget $K$ further characterize performance trade-offs oriented toward ranking quality.

cs.LG↗

arXiv2026

MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves

Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.

cs.LG↗

arXiv2026

To Keep or Not to Keep: Learning KV Cache Retention in Disaggregated LLM Serving Systems

Disaggregated \textsc{LLM} serving separates prefill and decode across node pools, placing a network fabric between \textsc{KV}-cache computation and consumption. This breaks a key assumption of classical cache policies: a miss no longer incurs only local recomputation, but also network transfer to the decode node. Likewise, admitting a block to the global cache requires an additional transfer, so poor retention decisions waste both memory and bandwidth. We present \textbf{KVLearn}, a learning-based framework for cost-aware \textsc{KV}-cache retention in disaggregated serving. KVLearn includes: (i) a lightweight Prefix Reuse Predictor (\textsc{PRP}) that estimates reuse probability from structural and temporal prefix features without modifying model weights; (ii) a Cost-Aware Retention Score (\textsc{CARS}) that converts reuse probability into keep/admit decisions using recomputation, transfer, and storage costs; and (iii) an Adaptive Threshold Controller (\textsc{ATC}) that adjusts admission thresholds online from observed hit rates and memory pressure. We integrate KVLearn into a globally disaggregated serving topology and evaluate it on text and multimodal workloads, including large image/video-derived \textsc{KV} blocks with heterogeneous reuse patterns. KVLearn reduces end-to-end time-to-first-token by up to 56% versus No-Cache, 38% versus LRU-Pool, and 33% versus Mooncake-style baselines, while cutting inter-node \textsc{KV} transfer volume by up to 53% versus LRU-Pool. On MM-Session, throughput remains within ${\sim}5%$ of oracle. Code is available at https://github.com/FastLM/KVLearn.

cs.LG↗

arXiv2021

Task Offloading and Resource Allocation with Multiple CAPs and Selfish Users

In this work, we consider a multi-user mobile edge computing system with multiple computing access points (CAPs). Each mobile user has multiple dependent tasks that must be processed in a round-by-round schedule. In every round, a user may process their individual task locally, or choose to offload their task to one of the $M$ CAPs or the remote cloud server, in order to possibly reduce their processing cost. We aim to jointly optimize the offloading decisions of the users and the resource allocation decisions for each CAP over a global objective function, defined as a weighted sum of total energy consumption and the round time. We first present a centralized heuristic solution, termed MCAP, where the original problem is relaxed to a semi-definite program (SDP) to probabilistically generate the offloading decision. Then, recognizing that the users often exhibit selfish behavior to reduce their individual cost, we propose a game-theoretical approach, termed MCAP-NE, which allows us to compute a Nash Equilibrium (NE) through a finite improvement method starting from the previous SDP solution. This approach leads to a solution from which the users have no incentive to deviate, with substantially reduced NE computation time. In simulation, we compare the system cost of the NE solution with those of MCAP, MCAP-NE, a random mapping, and the optimal solution, showing that our NE solution attains near optimal performance under a wide set of parameter settings, as well as demonstrating the advantages of using MCAP to produce the initial point for MCAP-NE.

cs.IT↗