Search arXiv⌕ Search

arXiv subjects

Yi Li

Publications and source records attributed to Yi Li.

At least 37 records · Page 2Linked to original sources
arXiv2026

SpecSyn: LLM-based Synthesis and Refinement of Formal Specifications for Real-world Program Verification

Program verification is a formal technique to rigorously ensure the correctness and fault-freeness of software systems. However, constructing comprehensive interprocedural specifications for full verification obligations is time-consuming and labor-intensive, giving rise to automated specification generation approaches. Despite the significant advancements in these approaches brought by Large Language Models (LLMs), existing LLM-empowered approaches still suffer from significant limitations: they lack effective strategies for handling sizable input programs, and are typically equipped with no mechanisms to evaluate and guarantee the strength of the generated specifications. The limitations impair their ability to extract precise specifications from real-world complicated programs to support the verification of target properties, thereby hindering the applicability of existing approaches in verification tasks on real-world programs. To remedy this gap, we propose SpecSyn, a novel LLM-based specification generation method. SpecSyn first decomposes the input program into individual segments, which are handled respectively by the subsequent iterative specification generation process. Innovatively, we incorporate into the process a specification refinement mechanism based on semantic-non-equivalent program mutations and variant discrimination, assessing and enhancing the semantic strength of the generated specifications. Extensive experiments show that SpecSyn maintains high precision over 90% and outstanding recall over 75%, significantly outperforming existing LLM-based approaches. In further evaluations, SpecSyn successfully handles 1022 out of 1421 target properties for open-source programs, proving its applicability on real-world program verification tasks.

cs.SE↗
arXiv2026

Conditional Multi-Event Temporal Grounding in Long-Form Video

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

cs.CV↗
arXiv2026

Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback

Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference-based training gives no explicit positive signal for unrecorded alternatives, and exact-match evaluation rejects non-matching predictions regardless of chemical plausibility. We propose Retrosynthesis via Reinforcement Learning from Forward Feedback (RetroRLFF), which optimizes reactant generation using both reference agreement and forward consistency with the target product. Starting from a supervised decoder-only Transformer, RetroRLFF generates complete reactant candidates and uses a frozen forward reaction model to predict products. A sequence-level reward combines reference agreement and forward consistency while penalizing invalid outputs. Direct Advantage-Based Policy Optimization updates the policy without human preference annotations or a preference-trained reward model. On USPTO-50K, RetroRLFF outperforms all 14 baselines in candidate-level round-trip accuracy at k = 1, 3, 5, and 10. With approximately 50 million parameters, it achieves 90.1% top-1 round-trip accuracy, exceeding R-SMILES, the strongest competing baseline on this metric, by 8.5 percentage points. Compared with its supervised policy, round-trip accuracy increases from 83.1% to 90.1%, while exact-match accuracy is maintained at 57.9% versus 57.5%. In an anonymized expert assessment of 131 randomly selected test cases, organic synthesis experts prefer RetroRLFF over EditRetro in 67.9% of comparisons. These results support forward feedback as a training signal for improving forward consistency while retaining top-1 reference recovery. Expert assessment provides complementary evidence of synthetic feasibility on the selected cases, although neither forward consistency nor expert preference establishes experimental feasibility.

cs.AI↗
arXiv2026

EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?

Autonomous agents have made rapid progress in general-purpose computer use, yet reliable automation of professional industrial engineering remains out of reach. Engineering workflows require reasoning over geometric and physical constraints and keeping dependencies consistent across software and design stages. We present EngiWorld, a benchmark designed around the capabilities that real engineering projects require, from operating a single application to solving engineering problems end to end. It contains 1,301 expert-curated tasks spanning six engineering domains (CAD, CAE, CAM, BIM, EDA, and DCC) and 26 professional software applications, with both GUI and CLI interfaces. The tasks are organized into six types, corresponding to capabilities that real engineering projects require. We further introduce an artifact-centric evaluation methodology built on a unified suite of domain verifiers. The verifiers programmatically check whether final and intermediate artifacts are geometrically valid, physically feasible, and compliant with design rules. Beyond binary success, they also score how well optimized designs meet their specifications. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model scores only 44.7/100, and just 3.6% of runs on tasks that require cross-software coordination succeed. EngiWorld provides a rigorous foundation for measuring progress toward agents that operate professional engineering software end to end.

cs.AI↗
arXiv2026

Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classes, domains, or compositions of tasks. In this paper, we introduce a Diffusion Meta-Prompt (DMP) model , a framework that models the distribution of learned prompts using diffusion models. Given a repository of previously learned prompts, DMP is trained and sampled without access to the original task examples or task losses, and synthesizes new prompts conditioned on natural language task descriptions. To improve the sampling stability, we introduce a test-time steering strategy for DMP, which uses the best training-selected prompt in the repository as a latent anchor during diffusion sampling, without retraining the DMP or accessing test classes. DMP improves generalization across classification, retrieval and text-to-image generation tasks, supports concept composition and negative prompting without explicit training. It reduces storage and inference costs by over 90% compared to prompt retrieval methods. For composite classification, DMP achieves upto 2.0% average gain over prior meta-learning methods across 55 pairs of datasets with gains as high as 8.5% on specific pairs such as Eurosat and Flowers. DMP also enhances cross-task generalization with ~2-9% improvement for hierarchical classification task. We further provide a theoretical guarantee bounding the expected task loss of prompts sampled from a DMP. Code is available: https://github.com/DeepakSridhar/dmp

cs.CV↗
arXiv2026

Gamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive Manipulation

Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because their training data is overwhelmingly Markov and mapping episodic memory directly to action chunks is hard. Yet the same policy, finetuned once to follow a privileged oracle's grounded-subgoal text, nearly solves these tasks: the difficulty lies entirely in mapping memory to a grounded symbolic subgoal. Existing work entrusts this stage to a single VLM that selects keyframes and reasons over raw frames, and falls far short of the oracle: key identities and dynamics are buried in noisy pixels, the reasoning spans hundreds of frames in an unbounded context, and hallucination corrupts the memory itself. We instead present GAMMA (Grounded multi-Agent Memory with Mechanical Audit), which builds the stage as a collaborating two-agent memory system: a detector tool (SAM-3) for spatial grounding, a VLM writer that distils each replan window into one grounded text line, an append-only text memory bank, and a VLM reasoner that reads the bank and emits the next grounded subgoal at the oracle's cadence, wrapped in a propose-verify harness that admits, defers, corrects, or rejects every agent claim against mechanical visual evidence, at training-corpus construction and at deployment alike. On a sixteen-task memory-manipulation suite GAMMA recovers a large fraction of the oracle ceiling with the policy held fixed, reaching the ceiling on several tasks, and transfers with unchanged contracts to a second benchmark.

cs.RO↗
arXiv2026

Can AI Scientists Coordinate at Runtime?

Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically relies on fixed workflows. In contrast, human scientists coordinate and adjust their division of labor at runtime. We therefore ask: can AI scientists also coordinate at runtime? To this end, we introduce Runtime Agent Coordination (RAC), which selects agents from existing AI-scientist hosts during execution, assigns scoped work contracts, and provides artifact-grounded verification. Verification informs subsequent agents without blocking transitions or discarding artifacts. We conduct a single-seed exploratory evaluation across Agent Laboratory, EvoScientist, and ARK on ResearchClawBench, preserving host models, tools, and permissions under host-calibrated budgets. Four cumulative conditions separate native execution, runtime communication, runtime selection, and the combined addition of contracts and verification. Runtime selection yields the highest observed mean score for each host; adding contracts and verification reduces these means, with host-dependent outcomes relative to native execution. These results motivate runtime coordination while exposing the limits of additional coordination mechanisms under constrained budgets. Code is available at https://github.com/systemind-team/Runtime-AI-Scientist.

cs.MA↗
arXiv2026

Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance

Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-executing unchanged requests can incur redundant computation. Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels. A meta-model first synthesizes a workflow of worker agents with declared roles, communication inputs, and tool permissions, and a separately prompted judge scores each executed candidate and diagnoses its deficiencies. In ordinary refinement rounds, \emph{workflow inheritance} starts from the latest completed candidate, may discard removable nodes judged unhelpful, and applies a validated edit to address the diagnosed deficiency. When the new candidate executes, \emph{execution inheritance} inherits eligible stored results only if the complete resolved request and execution context match, avoiding redundant model and tool calls. With GPT-4o-mini workers, Inherit-MAS achieves 55.4\% completion on WorkBench and 49.7\% joint F1 on HotpotQA FullWiki, outperforming EvoAgent, EvoMAS, and TacoMAS. With Qwen3-32B workers, it also exceeds these evolving-MAS baselines on both benchmarks. Compared with rerunning the same controller with execution inheritance disabled, execution inheritance reduces worker-token usage by 29.1\% on WorkBench and 34.6\% on HotpotQA, and total token usage by 5.3\% and 18.1\%.

cs.LG↗
arXiv2026

Highly Tunable Photon-Magnon Coupling Governed by Collective-Mode Profiles in Reconfigurable Dielectric-Resonator Arrays

The spatial structure of a microwave photon mode provides a degree of freedom for controlling its interaction with a localized magnetic excitation. We demonstrate site-selective magnon-photon coupling in modular arrays of discrete dielectric resonators mounted on a common microstrip line. The resonators can be added, removed, or rearranged on the same completed PCB, enabling post-fabrication geometrical reconfiguration of the collective photon modes and their nodal structure. A YIG sphere is positioned successively above individual resonators, while an in-plane magnetic field tunes its Kittel mode through the collective photon resonances. In a three-resonator array, modes with finite local microwave magnetic fields hybridize with the magnon at every measured site, whereas a mode containing a central field node exhibits no resolvable splitting when the sphere is positioned at that node. Full-wave simulations and a coupled-mode model show that the interaction is governed by the local amplitude of the collective photon mode rather than by spectral resonance alone. Extending this local-node selection rule to a five-resonator array successfully predicts the measured position-dependent coupling patterns. These results establish post-fabrication control of spatial magnon-photon hybridization and provide a route toward reconfigurable magnonic interfaces in future hybrid quantum microwave architectures.

cond-mat.mes-hall↗
arXiv2026

Development of Neutron Transmutation Doped Germanium (NTD-Ge) for Cryogenic Applications

This paper presents the systematic fabrication and characterization of cryogenic thermometers based on neutron transmutation-doped germanium (NTD-Ge). High-purity (10N) germanium samples were irradiated by thermal neutrons with different fluences at the China Advanced Research Reactor (CARR). After irradiation and a six-month cooling-down period, positron annihilation lifetime spectroscopy and temperature-dependent Hall effect measurements were performed to characterize irradiation-induced defects and carrier concentrations in the NTD-Ge samples. Utilizing standard semiconductor fabrication techniques, point electrodes were deposited onto the processed samples to fabricate functional NTD-Ge cryogenic thermometers. The low-temperature resistance performance of the devices was characterized down to 20 mK on a millikelvin range cryogenic test platform. The measured temperature dependence of resistance follows Mott's law, showing excellent agreement across the full measured range. The extracted T0 is consistent with expectations. These results collectively verified both the applicability of the thermometers in cryogenic system and the reliability of the fabrication procedure.

physics.ins-det↗
arXiv2026

Butterfly Effect Confirmed in Global AI Weather Models: Evidence from Tropical Cyclone Forecasting

A paradox recently emerged in artificial intelligence (AI) weather prediction research. While some claim AI weather models cannot simulate atmospheric butterfly effect, this conflicts with AI models' limited predictability and advances in AI ensemble forecasting. This study demonstrates via counterexamples that the butterfly effect does exist in AI weather predictions. For Super Typhoon Khanun, AI predictions are constrained by a double-attractor system. Minor initial perturbations confined to two regions trigger state transitions between two local attractors, causing a 1006-km difference in the predicted storm position on Day 7. This behavior is consistent with numerical weather prediction models and observed in ~12% of tropical cyclones in the past 5 years. These findings verify AI's ability to capture atmospheric chaos and provide the physical basis for AI ensemble forecasting.

physics.ao-ph↗
arXiv2026

TasmScan: Continuation-Aware Taint Analysis for TVM Bytecode with Savelist Abstraction

The Open Network (TON), with a peak market capitalization exceeding $20 billion and over 175 million activated on-chain addresses, relies on the TVM (TON Virtual Machine) to execute smart contracts. TVM uses first-class continuations with savelists to manage control flow and register state across continuation invocations. Since savelist-captured registers allow data to flow across continuation boundaries without passing through the operand stack, bytecode-level analyses cannot construct complete data flow tracking without explicitly modeling savelist semantics. We present TasmScan, the first bytecode-level static analysis framework for TVM that enables cross-continuation data flow reasoning without requiring source code. TasmScan models savelist semantics via forward register analysis with a formal over-approximation guarantee for exact-resolved save sites and locally tracked register definitions, then lifts bytecode into TASIR, a typed intermediate representation, and performs path-sensitive taint analysis with context-aware sources to detect defects. We evaluate TasmScan on 2,921 contracts from the TON verifier registry and a labeled benchmark of 208 contracts with human-confirmed ground truth. On the full corpus, TasmScan resolves 294,546 dynamic continuation targets with 100% precision; ablation confirms that savelist propagation is essential for resolving indirect register calls that depend on cross-continuation register passing. On the benchmark, TasmScan detects 95.3% of defects across five classes with 96.8% precision. A 366-pair stratified sample from the full corpus estimates 85.8% overall precision. TasmScan offers a 17x median speedup over the state-of-the-art symbolic-execution baseline, and in the path-analysis comparison completes 100% of analyses with zero crashes or timeouts.

cs.SE↗
arXiv2026

Verification of Compiler-to-Accelerator Mappings for Machine Learning Accelerators

To meet the performance needs of modern machine learning (ML) applications, ML compiler frameworks support compiler-to-accelerator mappings that offload parts of application code to operations in specialized hardware accelerators. However, most of these frameworks do not verify these mappings down to the hardware level, potentially resulting in functional mismatches. In this paper we propose BOLT, the first framework for formally verifying the correctness of compiler-to-accelerator mappings for coarse-grained intrinsics in ML accelerators, with respect to a formal hardware semantics. BOLT does not require additional information from the compiler, and verifies the functional equivalence of the application code and the code for the mapped hardware accelerator intrinsic, including handling of complex loop nests and tensor data layouts in hardware. It effectively utilizes a pattern of *aligning* software loops with the hardware, followed by *relating* corresponding data layouts, to enable verification using well-aligned product programs. To support these steps, we propose two custom templates --- the sync-skeleton and the layout-sketch --- to guide users in aligning loops and specifying data layout relationships, respectively. We have developed a proof-of-concept prototype for BOLT and use it to successfully verify the correctness of several complex mappings for two recent open-source ML accelerators.

cs.PL↗
arXiv2026

Context-dependent agent evaluation with orthogonal equilibrium learning

Many applications require to evaluate agents under contextual information (e.g., a prompt, task, or user group). We study how to perform such context-dependent agent evaluation from offline feedback. Existing score-based models for this purpose (e.g., Bradley-Terry) impose a transitive preference ordering, which fails to reflect collective preferences when human judgements are heterogeneous. Inspired by social choice theory, we frame evaluation as a contextual game between two players, each selecting a distribution over agents as the strategy to receive greater collective preference than the other. Then, the support of the Nash equilibrium defines a context-specific set of winners. However, learning context-specific equilibria from offline logs is difficult because each context reveals human feedback on only a subset of agents, and, hence, a naive plug-in estimator can therefore be biased. To address these challenges, we propose NashEval, a general framework for robust contextual equilibrium learning. NashEval first constructs debiased estimates of the contextual payoff matrix that characterizes the game. NashEval then learns the context-to-equilibrium mapping with a tailored orthogonal loss, which avoids the need to solve a separate game for each context. We show theoretically that errors in estimating the nuisance functions underlying the payoff matrix affect the risk of the learned equilibrium (i.e., exploitability) only through higher-order terms. Across various experiments, NashEval improves robustness of equilibrium learning and consistently identifies the set of top-performing agents across contexts.

cs.AI↗
arXiv2026

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.

cs.AI↗
arXiv2026

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one another. We ask whether that appearance rests on a model of the partner's mind or on the surface record of what the partner said. We build a social simulation in which both questions have exact answers: 40 multi-issue negotiations whose hidden preference weights and whose full Pareto frontier are known by construction. Two model families negotiate across 160 dyads, every transcript is frozen before any measurement, and 2880 counterfactual probes then hold the evidence byte identical while moving one factor at a time: the reader's own stake, the partner's tone, an identity label, and the order of recursion. The agents are socially fluent and economically poor. They reach agreement in 96.2% of dyads with 0 protocol failures, yet only 0.7% of deals land on the Pareto frontier, they leave 20.5% of the available joint value unclaimed, and they miss the one issue on which their interests are perfectly aligned in 76.6% of deals; on the frontier and on that aligned issue, a package drawn at random from the set both sides would accept does as well. The probes locate the failure. Swapping only the reader's own payoff sheet, while the partner's words and offers stay identical, moves the inferred top priority by 15.0 percentage points, which is egocentric projection rather than inference, while a tone rewrite moves it by 5.3 percentage points and an identity label by 0.0. Most tellingly, an agent predicts what its partner believes about it 72.5% of the time while that partner's belief is itself correct only 51.2% of the time: the agents track the conversation far better than they track the mind behind it.

cs.LG↗
arXiv2026

Sample-Conditioned Representation Selection for Audio Few-Shot Learning

Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift. On SpurAudio, the resulting representation shift is concentrated and class dependent: for ResNet12, the top 10 percent of channels explain 82.80 percent of the null-corrected shift contribution. We propose SAMPLESELECT, which predicts a fixed-budget feature mask independently for each input while keeping the encoder and source classifier frozen. Training uses differentiable Gumbel Top-k selection with foreground classification and cross-background contrastive losses; inference uses deterministic Top-k masks and support-only linear adaptation. Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points. Ablations and representation analyses further support the learned selection mechanism. Code is available at https://github.com/Cross-Innovation-Lab/SAMPLESELECT/

cs.AI↗