All Updates

Page 601 of 610

February 12, 2026

๐Ÿ“„
ArXiv AIโ€ข52d ago

OmniSapiens: HARPO for Social Behaviors

OmniSapiens-7B 2.0 uses HARPO RL to train a unified model across heterogeneous social tasks. HARPO balances learning via modulated advantages. It outperforms baselines by up to 16.85% with robust reasoning.

#research#omnisapiens#7b-20
๐Ÿ“„
ArXiv AIโ€ข52d ago

NSAM: Neuro-Symbolic Action Masking in DRL

NSAM learns symbolic models and action masks automatically during DRL to avoid infeasible actions. It integrates symbolic reasoning with deep policy optimization mutually. Evaluations show improved sample efficiency and fewer violations.

#research#nsam#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

Neurosymbolic AI Conquers Schauder Theory

White paper integrates nonuniform ellipticity breakthrough with topos-theoretic LRMs. Formalizes sharp Schauder estimates using ghost equations. Enables autonomous proofs in calculus of variations.

#research#neurosymbolic-lrms#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

NAEs Balance Interpretability and Accuracy

Neural Additive Experts use mixture-of-experts per feature with context-gated integration for flexible additivity. Targeted regularization ensures smooth transitions from additive to interactive models. Outperforms on accuracy while preserving feature explanations.

#research#nae#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

Multi-Layer AI Malware Detector

SecureScan uses logistic regression, heuristics, and VirusTotal for URL/file/binary triage. Achieves 93.1% accuracy with balanced precision/recall. Employs gray-zone logic to cut false positives.

#research#securescan#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

MoE for Drift-Aware Malicious Traffic Detection

MalMoE detects encrypted malicious traffic using graph-based Mixture-of-Experts to handle graph drift. It selects optimal 1-hop-GNN experts via a redesigned gate model. Trained with two-stage strategy and augmentation for real-time precision.

#research#malmoe#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

MLLMs Survey on Chart Fusion

Survey organizes MLLM evolution for chart understanding via multimodal fusion. Introduces taxonomy of tasks and datasets. Highlights limitations in perception and reasoning, suggesting alignment and RL enhancements.

#research#mllms#survey
๐Ÿ“„
ArXiv AIโ€ข52d ago

MIPLIB-NL for Industrial Optimization Benchmarks

MIPLIB-NL creates natural-language optimization benchmarks from real MIPLIB 2017 instances via structure-aware reverse engineering. Includes 223 validated reconstructions tying NL specs to solver code. Reveals LLM failures on large-scale problems.

#research#miplib-nl#optimization
๐Ÿ“„
ArXiv AIโ€ข52d ago

MetaphorStar Masters Image Metaphor Reasoning

MetaphorStar uses end-to-end visual RL for image metaphor understanding, featuring TFQ-Data dataset, TFQ-GRPO method, and TFQ-Bench. MetaphorStar-32B sets SOTA on implication benchmarks, outperforming 20+ MLLMs including Gemini-3.0-pro. Improves general visual reasoning via scaling analyses.

#research#metaphorstar#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

MERIT Boosts LLM Negotiation Skills

AgoraBench tests LLMs in nine bargaining scenarios like deception; utility metrics measure human alignment. MERIT feedback via prompting/finetuning elicits deeper strategy and opponent awareness. Outperforms baselines in negotiation power and acquisition.

#research#agorabench#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

MEL Boosts LLM Reasoning via Meta-Experience

Meta-Experience Learning (MEL) enhances RLVR by internalizing error-derived meta-experience into LLM memory. Uses self-verification for contrastive analysis of trajectories. Achieves 3.92%-4.73% Pass@1 gains across model sizes.

#research#mel#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

MeCSAFNet Boosts Multispectral Segmentation

MeCSAFNet uses dual ConvNeXt encoders for visible and non-visible channels in multispectral land cover segmentation. It employs smooth attentional feature fusion with CBAM and ASAU activation. Outperforms baselines like U-Net and SegFormer by up to 19% mIoU on FBP and Potsdam datasets.

#research#mecsafnet#base-large
๐Ÿ“„
ArXiv AIโ€ข52d ago

LRMs Fail to Transfer Reasoning to ToM

Study compares reasoning vs non-reasoning LLMs on ToM benchmarks, finding no consistent gains and sometimes worse performance. Insights reveal slow thinking collapse, need for adaptive reasoning, and option-matching shortcuts. Interventions like S2F and T2M mitigate issues.

#research#tom-study#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LOREN: Low-Rank Adaptation for Neural Receivers

LOREN introduces low-rank adapters to enable code-rate adaptation in neural receivers without storing separate weights. It freezes a shared base network and trains lightweight adapters per code rate. Achieves comparable performance with major hardware savings.

#research#loren#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LoRA Enables Modular Chemistry Prediction

Evaluates LoRA for parameter-efficient fine-tuning of LLMs on organic reaction datasets like USPTO and C-H functionalisation. Matches full fine-tuning accuracy while preserving multi-task performance and mitigating forgetting. Reveals distinct reactivity patterns for better adaptation.

#research#lora#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

Locomo-Plus Tests LLM Cognitive Memory

Locomo-Plus benchmarks cognitive memory in LLM agents under cue-trigger disconnects, focusing on latent conversational constraints. It proposes constraint consistency evaluation over string-matching. Reveals gaps in existing memory systems.

#research#locomo-plus#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LLMs Tackle Agent-Based Model Replication

Study evaluates 17 LLMs on ODD-to-Python code generation for predator-prey model. Assesses executability, fidelity, efficiency via NetLogo baseline. GPT-4.1 excels, but reliability varies.

#research#llms#gpt-4-1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LLMs Predict Stroke Outcomes from Notes

Fine-tuned LLMs like Llama predict mRS scores from admission notes alone. Achieves 33.9% exact 90-day accuracy and 76.3% binary, matching structured baselines. Enables seamless clinical integration without data extraction.

#research#stroke-llm#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LLMs Outstrategize Humans in Games

Uses AlphaEvolve to discover interpretable models of human and LLM strategic behavior from data. Analysis on iterated rock-paper-scissors shows frontier LLMs capable of deeper strategy than humans. Provides foundation for understanding behavioral differences in interactions.

#research#alphacevolve#v1
๐Ÿ“„
ArXiv AIโ€ข52d ago

LLMs Generate Planning Abstractions

Prompts pretrained LLMs to create QNP abstractions for generalized planning from domains and tasks. Automated debugging detects/fixes errors iteratively. Guided LLMs produce useful abstractions for qualitative numerical planning.

#research#qnp-generator#v1
Page 601 of 610