Research

• Compositionality in RAG pipelines1 paper raises it · 1 addresses it

  Combining individually strong RAG components often fails to improve overall performance, and gains may not transfer across retrieval quality and answer faithfulness.

  • Retrieval Augmented Generation Compositionalityraises · addresses
• Request execution in streaming video generation1 paper raises it · 0 address it

  Models struggle to reliably follow incremental multimodal requests while maintaining state consistency and visual fidelity.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution harnesses may demand behaviors the model has not learned or restrict existing capabilities.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Evidence-grounded evaluation for audio-visual reasoning1 paper raises it · 1 addresses it

  Existing benchmarks often allow models to answer correctly without analyzing necessary audio-visual evidence, weakening reliability.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses

Named by an AI from these papers' abstracts.

• Federated learning47+6.8%
• Anomaly detectors350.0%
• Machine learned interatomic53−1.9%
• Forecasting time77−3.8%
• Adversarial training48−4.0%
• Frontier LLMs463−8.5%
• Agents517−10.6%
• 3D scene158−10.7%

• arXiv cs.CVComputer visionOct 14▲ 2

  VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution

  Hairong Ni, Jiahe Huang, Minghao Guo, Wojciech Matusik, Rose Yu

  Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomically unsupported vascular detail, such as missing, spurious, or incorrectly connected vessels. To overcome this challenge, we introduce VascuSR, an iterative anatomy-aware diffusion framework that combines image reconstruction with explicit 3D vascular guidance. First, to provide richer anatomical guidance, we use an explicit 3D vascular representation that captures structural information beyond individual slices. This representation also simplifies vascular refinement by allowing a lightweight 3D generative refiner to focus on vascular structure rather than complex CT appearance. Second, to guide slice-wise SR, a lightweight anatomy controller injects the refined structure into the diffusion decoder, while iterative feedback updates this guidance from each new SR volume. On re-annotated MSD Task08 and HVM datasets, VascuSR outperforms interpolation and learning-based SR baselines in…

  AI60PDF

  Summarize this
• arXiv cs.CLInference & servingOct 14▲ 3

  ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models

  Bohan Sun, Zunhai Su, Xialie Zhuang, Jianjin Li, Ngai Wong +1

  Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden features whose contextual emphasis may not align with the needs of subsequent draft positions. Hybrid linear attention (HLA) models maintain compact recurrent states that accumulate historical associations, offering an efficient source of complementary context for speculative drafting. We introduce ReaDy, the first speculative decoding method, to the best of our knowledge, to leverage HLA recurrent states for position-specific context retrieval during drafting. ReaDy equips each draft position with a learned query to retrieve supplementary context directly from the target's committed recurrent states. A lightweight state reader integrates this context into draft representations through residual updates, while low-rank state reads and fused operators keep additional computation and I/O overhead low. Building on DSpark's parallel backbone and sequential prediction head, ReaDy employs a lightweight two-stage adaptation strategy, with reader capacity, state sources, and residual placement examined through ablation studies. Across seven…

  AI80Code
• arXiv cs.LGOct 14

  Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records

  Jin-Jia Zheng, Vincent S. Tseng

  Longitudinal electronic health records (EHRs) can reveal disease-progression structure, while useful forecasting requires leakage-controlled discovery, censor-aware outcomes, and inspectable trajectory evidence. We developed a graph-enhanced framework in MIMIC-IV v3.1 that splits patients before graph construction, learns train-only consecutive-admission transitions, and freezes endpoint-specific branching-motif policies selected on validation data. The final catalog contained 99,527 motifs, and a time-aware Transformer retrieved at most 24 patient-compatible motifs per endpoint through endpoint-specific cross-attention. Across five training seeds, micro-AUPRC increased from 0.9330 to 0.9357, while event-time MAE decreased from 676.9 to 657.7 days (reduction 19.2 days; 95% paired patient-cluster bootstrap CI, 13.8-24.8). Timing effects were heterogeneous: MAE worsened for events within 730 days but improved by 58.9 days for events occurring after 730 days. In an exploratory internal temporal split, branch conditioning reduced conditional event-time MAE by 26.9 days (95% CI, 23.0-30.8) without evidence of better micro-AUPRC. Corrected survival evaluation over the supported…

  AI10PDF

  Summarize this
• arXiv cs.CVComputer visionOct 14

  OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation

  Yini Li, Joanne Lin, David Blackham, David Bull, Nantheera Anantrasirichai

  Low-light video processing remains an underexplored problem in computer vision, primarily due to the scarcity of high-quality ground-truth data. Existing public datasets exhibit several limitations, including restricted motion diversity, limited scene coverage, weak degradations, reliance on auxiliary modalities such as event data, and misalignment between low-light inputs and ground truth. Furthermore, current datasets typically address either low-light enhancement or scene understanding, whereas these tasks should be considered jointly. We introduce \textbf{OLiVES}, a benchmark dataset for outdoor low-light videos with dynamic scenes, designed to support both low-light video enhancement (LLVE) and video object segmentation (VOS). The dataset addresses key content gaps by incorporating a diverse range of natural textures, animals, occlusions, dynamic activities, and close-up scenes. To the best of our knowledge, OLiVES is the first outdoor low-light video dataset captured using professional cinema-grade cameras. It provides over 25,000 aligned normal- and low-light frame pairs, along with over 46,000 VOS annotations. We benchmark state-of-the-art LLVE and VOS methods on OLiVES…

  AIEvals60PDF
• arXiv cs.LGTraining & fine-tuningOct 14

  Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling

  Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng +7

  Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual reasoning tokens or actions remains difficult. Group-relative methods such as Group Relative Policy Optimization (GRPO) sample several attempts per prompt, but lose their reward-based learning signal when all attempts receive the same outcome. We propose Hindsight-Privileged RLVR (HP-RLVR), a single-rollout method that turns a completed trajectory's own future into token-level update weights. The generating policy snapshot scores each eligible token under its causal history and under a hindsight context containing the realized future and verifier feedback. A normalized Jensen--Shannon divergence between the two views weights the reward relative to a historical baseline, yielding bounded token credit for both successful and failed attempts, with no reference solution or learned critic. In paired Qwen3-8B runs over a shared $100$-step schedule, HP-RLVR trains $1.21\times$, $1.46\times$, and $2.30\times$ faster than GRPO on mathematics, code generation, and ALFWorld, using one eighth the rollouts per prompt. Accuracy is comparable…

  AI70PDF

  Summarize this
• arXiv cs.CVAI safetyOct 14

  Quantifying privacy risks in foundation model representations of brain MRI

  Imen Bajar, Héber Hwang Arcolezi, Antoine Boutet, Carole Frindel, Mohamed Maouche

  Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is unclear how much patient-specific information these representations retain. We investigate this question for brain magnetic resonance imaging (MRI) by evaluating five frozen pretrained encoders spanning different architectures, pretraining objectives, and training domains on two longitudinal T1-weighted datasets, OASIS-2 and MIRIAD. Under an attacker model with access to released embeddings, the corresponding public encoder, and auxiliary MRI scans, we evaluate patient linkage and sensitive-attribute inference. Across the evaluated representations, we observe substantial subject-specific information: rank-1 patient linkage reaches up to 99\% on MIRIAD and exceeds 90\% on OASIS-2 for the highest-risk representation, despite the absence of an identification objective during encoder training. We further show that the released embeddings retain information about a demographic attribute, with recorded-sex prediction reaching balanced accuracy of 90.9\% on OASIS-2 and 95.5\% on MIRIAD. Overall, our results demonstrate that replacing raw…

  AI70PDF

  Summarize this
• arXiv cs.LGOct 14

  Average-Reward Policy Identification from a Single Continuing Trajectory

  Tongxi Wang

  In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any state--action pair, an agent learning from a single trajectory must spend additional time navigating between states. It is therefore natural to expect that learning from a single trajectory requires more experience. In this paper, we show that this additional cost is not always necessary. For average-reward reinforcement learning, we develop an algorithm that learns where to collect information while ensuring that the required samples can be obtained efficiently. We establish an upper bound on the number of interactions needed to identify a near-optimal policy. Furthermore, we prove a matching information theoretic lower bound, showing that, for a broad class of environments and at sufficiently high accuracy, learning from a single trajectory is no harder in the worst case than learning with unrestricted access to state action samples. Our results reveal that the additional complexity cost of navigation can be avoided by adapting information gathering requirements to how the environment provides information.

  AI30PDF

  Summarize this
• arXiv cs.LGInference & servingOct 14

  Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling

  Weixin Wang, Wei Deng, Anderson Schneider, Yuriy Nevmyvaka, Pan Xu +1

  We study how to improve LLM reasoning at inference time without updating model weights or using external reward models. Recent reward-free power-sampling methods define the sequence-level power target $π_α(y\mid x)\propto p_0(y\mid x)^α$, where $α>1$, which increases the relative probability of completions that are already likely under the base model. Existing methods use Metropolis--Hastings or Sequential Monte Carlo (SMC) to approximately sample from this target. However, two challenges arise at different levels. At the target level, full-sequence sharpening can concentrate probability on a few exact reasoning--answer trajectories, suppressing alternative paths that support the same answer. At the sampler level, finite-particle SMC can suffer from path collapse when resampling repeatedly duplicates a few high-weight prefixes. To address these challenges, we propose Decoupled Marginal Sharpening (DMS), which separately controls how strongly the model favors particular reasoning paths and how strongly it favors final answers after aggregating support across those paths. At the target level, DMS first samples from a sharpened reasoning distribution, then marginalizes the model's…

  AI70PDF

  Summarize this
• arXiv cs.CLAI safetyOct 14

  Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models

  Harsh Kumar

  Bias audits of multilingual language models usually compare a model's average stereotype score in English with its average in another language and read the difference as a difference in fairness. We ask how much of that difference is noise. Auditing ten open models in eight languages, we measure how far scores move when English test items are merely reworded, test every language shift item by item, and check that the test catches shifts we inject on purpose. In all 70 model-language pairs the stereotype score falls below its English level, and for Hindi, Korean and Swahili the drop clearly exceeds what rewording English produces; most of it comes from StereoSet items. Judging every translation, we find that imperfect ones drop more, but faithful translations alone drop nearly as much. Still, a lower average does not show that a model is fairer. An item's English score predicts its translated score far less well than its reworded score (correlation 0.23, 0.27 on faithful translations, vs. 0.48), while scores stay as far from neutral, models agree on translated items, and within Hindi or Spanish a translated item's score correlates with its own rewording at 0.84 and 0.82. The…

  AI70PDF

  Summarize this
• arXiv cs.CLRoboticsOct 14

  AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents

  Peidong Wang, Ying Chang, Zhiming Ma, Xiaocui Yang, Shi Feng +6

  Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, but embodied RSI methods either refine the harness around a frozen executor and so cannot add a missing motion, or train the executor on persistent failures without asking whether a failure lies in how the executor is called or in what it can do. We ask when a self-improving embodied system should change the weights of its executor, and propose AdaRSI, an on-demand RSI framework for embodied agents. A coding agent first improves its skills and harness, then attributes persistent failures by retrying failing sub-steps from saved states, and fine-tunes only the sub-steps that remain unreliable, with demonstrations it collects itself and experience carried over from earlier tasks. On all 50 target tasks of RoboCasa365, with GR00T N1.5 as the executor and no human demonstrations, AdaRSI improves the VLA on all three suites and raises its success on unseen composite tasks from 4.6% to 13.8%. Compared with fine-tuning every sub-step, it reaches slightly higher success while using only 28% of the GPU time and 22% of the self-collected…

  AIAgents80Code
• arXiv cs.AIOct 14

  SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift

  Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang +2

  Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem using only information available before each decision. At each decision the controller asks two distinct questions: what local downside a deviation from the frozen anchor would induce under matched legal continuations, and what future adaptation value would be lost by consuming part of the remaining deviation budget now. The first question is answered by a monotone strategic-risk model over deviation intensity; the second by a paired budget-state continuation model that prices current budget consumption. The controller selects among support-preserving candidate deviations by trading immediate adaptation value against these two quantities, a pathwise cumulative-KL ledger bounds total anchor-relative deviation, and a finite family of frozen controllers is screened on complete paired calibration sessions before held-out interaction. A finite-candidate perturbation bound shows that the allocation objective degrades continuously with continuation-value estimation error. Evaluation covers exact-game exploitation…

  AI20PDF

  Summarize this
• arXiv cs.CLEvalsOct 14

  ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models

  Rusali Saha, Nitya Khurana, Ruihong Huang, Kuan-Hao Huang

  Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute of a country or region. We introduce ChronoCulture, a benchmark of 10,360 temporal pairs built from longitudinal survey data across 72 countries. Each pair contains the same survey question asked in the same country in an older and a newer year, with full population response distributions as ground truth. Across six LLMs, we find that models can often predict a country's attitudes at one point in time but do not reliably capture how those attitudes change. Their predictions for different years tend to stay close together, failing to capture much of the observed change. Specifying the intended year in the prompt also offers little overall improvement in alignment with survey responses. These findings suggest that models often present a largely static picture of cultural attitudes, highlighting the need to evaluate cultural awareness across time.

  AI70PDF

  Summarize this
• arXiv cs.LGInference & servingOct 14

  RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention

  Shiyu Ji, Peng Ling, Chen Lin, Shupeng Li, Yixuan Wang +2

  Multi-head latent attention (MLA) compresses the content of a key-value cache into a shared latent per token, making low-bit storage attractive for long-context inference. At two bits, errors in this representation perturb both attention matching and value readout, with effects that depend on error direction and reconstruction scale. We introduce RoLaQ (Rotation-calibrated Latent Quantization), an offline method for joint rotation and range calibration. RoLaQ refines a shared rotation within subspaces defined by the frozen key and value projections, and jointly learns quantization ranges whose thresholds and reconstruction gains are coupled to control the shared signal's response. Prediction matching and attention-output supervision guide calibration with model weights frozen. Across three MLA models and six benchmarks, RoLaQ achieves the highest average accuracy among the compared 2-bit methods both without and with token protection. On DeepSeek-V2-Lite, an SGLang implementation provides 3.96 times the BF16 KV capacity under the same memory budget and 2.51 times its decode throughput with 256K input tokens.

  AI80PDF

  Summarize this
• arXiv cs.LGOct 14

  Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning

  Parham Nooranbakht, Seyed Mahdi Basiri Azad, Joschka Bödecker

  Value-based Q-learning for continuous control can discretise the action space, but the resolution of the discretisation trades early exploration against final precision. Growing Q-Networks (GQN) grow the resolution uniformly from coarse to fine. We introduce Selective Growing Q-Networks (SGQN), which keeps decoupled Q-learning and replaces uniform growth with an adaptive action grid: bins are added next to bins with high estimated Q-value, bins with low Q-value are pruned, and actions are chosen epsilon-greedily. On eight DeepMind Control Suite (DMControl) tasks with 2 to 12 action dimensions, SGQN has the highest mean final return among the compared methods on four, is within 1.1% of the best method on three more, and is 3.4% below Bang-Bang MPO on Walker Run, using on average 7.5 of 9 available bins per dimension. We then test whether the adaptive grid explains these results, and find that it does not. Growth activates every candidate bin and behaves like uniform growth, and removing pruning changes the return by at most 1.1%. Two other choices matter: starting from a coarse grid, since starting with all 9 bins produces collapsed seeds, and epsilon-greedy selection, since an…

  AI30PDF

  Summarize this
• arXiv cs.LGCode modelsOct 14

  Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model

  Olayiwola Arowolo, Oluwadara Adedeji, Peter Palensky, Jochen L. Cremer

  Foundation models have shown strong generalization across scientific domains, but their use in power systems remains largely task-specific. We investigate whether a pretrained tabular foundation model (TFM), TabPFN, can serve as a general-purpose neural solver for power grid steady-state analysis. We evaluate the TFM on three tasks: power flow (PF) prediction, N-k contingency screening (NCS), and voltage stability margin (VSM) prediction. We performed experiments on 118- and 2000-bus systems, comparing the TFM against task-specific neural baselines. Without retraining or fine-tuning, the TFM matches or outperforms the best task-specific model in several settings across the three tasks. For 118-bus PF prediction, a variant of the TFM achieves errors of $1\times 10^{-3}$ pu for voltage magnitudes and $0.30^\circ$ for voltage angles, outperforming all baselines. On unseen N-1 contingency and close-to-infeasible PF cases, the TFM is competitive with the DCPF approximation. For millions of unseen N-2 contingencies, the TFM achieves AUCs of 0.92 and 0.95 for branch and voltage violation screening, respectively. The TFM also attains accurate VSM prediction performance for the 2000-bus…

  AIEvals70PDF
• arXiv cs.CLEvalsOct 14▲ 2

  Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR

  Nguyen Nguyen, Yongyi Zang

  Character Error Rate (CER), the standard metric for OCR and vision-language models (VLMs), charges a typo as much as a wrong name. We introduce semCER, which keeps CER's alignment and denominator and charges each grapheme edit a severity from an LLM judge, with no word segmentation. Normalized CER keeps the score of a whole transcription, where it tracks readers as well as semCER or better, and semCER breaks that score down into named edits. The charges track readers' ratings edit by edit in English, Vietnamese, and Chinese and put the edits readers rate most severe near the top of a sorted list. On pairs drawn where CER and semCER disagreed, readers side with semCER more often than with normalized CER in English and Chinese, and equally often in Vietnamese. Across 16 languages, the judge charges a wrong diacritic or tone mark almost nothing in Spanish but nearly a wrong letter's severity in Telugu. Where we can count real words, a general VLM's wrong letter forms one far above chance while a classical pipeline's stays near it. We release the 61 million judged edits, the aggregated reader ratings, and the distilled scorer at https://github.com/nguyenx2t/semcer.

  AI70Code
• arXiv cs.CLCode modelsOct 14▲ 6

  MolLean: A Process-Verifiable Language for Chemical Reasoning

  Jiatong Li, Yatao Bian

  Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph edits to compound transformations. Meanwhile, a typed witness protocol separates native structural checks from externally supplied measurements. We further introduce MolLean-MCP, a stateful tool interface that exposes these transitions, checks, and readouts during generation: the model receives feedback to decide its next action, and rejected actions leave the state unchanged. MolLean supports one-pass trace execution, whole-trace refinement, and interactive reasoning through MolLean-MCP. We evaluate these three modes with direct chain-of-thought on 8,800 matched examples across 12 tasks spanning molecular generation, editing, optimization, and reactions. With Qwen3.6-27B, whole-trace refinement outperforms direct chain-of-thought on all 12 tasks. MolLean-MCP complements whole-trace refinement with stepwise verification feedback, reaching better performance in…

  AIAgents80Code
• arXiv cs.CLAgentsOct 14

  Same Claim, Different Interpretations: How LLM Agents Resolve Ambiguity in Scientific Claims

  Delip Rao, Ahmed Muharram, Chris Callison-Burch

  Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences. Natural-language scientific claims, written for human experts, are often underspecified and so admit several defensible interpretations. Such verifiers usually pick one, often tacitly, and benchmarks score their verdicts against expert labels without recording the expert's interpretation or the verifier's in a comparable form. This leads to disagreements with expert labels that cannot be traced to the evidence or the interpretation, and to compute spent on unchecked interpretations. We introduce Claim Cards to make such interpretations explicit in the reasoning itself. A Claim Card records a verifier's interpretation as nine fields before evidence gathering, each marked stated, inferred, or default. To test whether an agent's interpretation can change its verdict, we ran a GPT-5.4 agent five times on each of 60 expert-labeled materials-science and biomedical claims with a card, without one, and with one card frozen across runs (900 runs). Over 40% of card fields were not marked stated, and a card added about a tenth to a run's GPT-5.4 tokens and time without measurably…

  AIEvals70PDF

  Summarize this
• arXiv cs.CVOct 14

  Automatic Cause Determination in Road Scene Understanding Using Qualitative Reasoning and Four-Valued Logic

  Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker

  Road scene understanding in automated driving (AD) aims to build a comprehensive analysis of video sequences taken on the road by embedded or fixed cameras (e.g., mounted on vertical road signals). One goal is to identify the relevant actors in the scene and another goal is to determine the causes that have triggered a specific action of the ego car (i.e., stop, slow down, turn left, etc.). In a complex urban environment, these causes can be multiple, confusing, possibly contradictory to other causes and not easily expressible using simplistic reasoning. Still, providing accurate {\it automatic cause determination} supports a) user acceptance by providing appropriate explanations to the car passengers and road users; b) increased road safety by providing detailed road scene understanding to traffic. In this paper, we propose using spatiotemporal reasoning and Belnap's four-valued logic to formulate complex causes of AD action in a road scene. We compute these causes by analysing a Qualitative eXplainable Graph (QXG), which is an abstract representation of the road scene capturing spatiotemporal relations between road entities. Starting from a QXG, our approach called \tool, is…

  PDF

  Summarize this
• arXiv cs.AICode modelsOct 14

  L2G-SR: Learning to Guide LLM-based Symbolic Regression

  Letian Huang, Xiangyu Wang, Haowei Lin, Di He

  Symbolic regression searches for an equation that explains observed data. Numerical error is commonly used to guide the search, but it alone can favor an accurate surrogate over a candidate with the right structure. We propose L2G-SR, a framework for LLM-based symbolic regression that guides search with a learned structural verifier. We construct structural supervision signal using tree edit distance (TED), accounting for commutative operators and alternative expression forms. A verifier first aligns numerical observations with the formulas, then learns to score a candidate's structural similarity to the target formula. At search time, the target formula is hidden and the verifier complements numerical error in parent selection. An analyst then uses verifier feedback and diagnostic tools to propose revisions, which a generator converts into refined expressions. On LLM-SRBench, L2G-SR achieves state-of-the-art numerical fit, equation level accuracy and TED across the evaluated LLM backbones and domains. L2G-SR demonstrates the value of learned structural guidance for LLM-based symbolic regression.

  AIEvals70PDF

  Summarize this