User as Engram proposes storing per-user facts as surgical, hash-keyed edits to a memory table, leaving reasoning in a shared adapter. This design achieves 5.6x higher indirect-reasoning accuracy and maintains base-level reasoning performance, with a memory footprint 33,000x smaller than per-user LoRA. The approach enables disjoint user edits that compose losslessly, outperforming retrieval pipelines beyond 100 facts.
Data Intelligence Agents (DIA) deploy autonomous coding agents to streamline enterprise data workflows. The Query Generator matches or exceeds top published results on seven SQL benchmarks across four dialects, showing generalization through natural-language instructions and execution-based architecture.
NoiseTilt introduces NTRK, a reward-guided diffusion sampler that injects reward gradients via the noise term without altering the reverse kernel. By using a whitening operator, NTRK safely biases noise toward high reward, preserving sample quality while maintaining strong guidance. On aesthetic generation, NTRK achieves superior reward performance with 25 NFEs, reducing compute by 20× compared to state-of-the-art baselines.
BinTrack is a fully open-source spatial question answering agent that uses binary search over a robot's trajectory to locate answers. It achieves up to 22.8% higher accuracy than other open-source methods and matches closed-source model performance on the most challenging global category of the SpaceLocQA benchmark. The system also offers over 1.5x faster inference and introduces GangnamLoop, a real-world outdoor benchmark collected with a quadruped robot.
Act2Answer introduces a lightweight protocol to assess commonsense and world knowledge retention in VLA models by requiring agents to answer questions through object placement actions. A large-scale study of 7 VLA models and 9 VLM baselines reveals that VLAs perform well on simple concepts but show larger gaps on rich semantic categories compared to their source VLMs, with VQA co-training improving knowledge retention and peak answer-relevant signals observed in middle VLA layers.
Sumi is a 7B-parameter uniform diffusion language model pretrained from scratch on 1.5T tokens. It competes with autoregressive models on knowledge, reasoning, and coding tasks but underperforms on commonsense benchmarks, likely due to its education-heavy data mixture. The model weights, checkpoints, and full training recipe are publicly released.
Morpheus is a morphology-aware neural tokenizer and word embedder for Turkish that preserves original text through lossless encoding and decoding. It achieves the lowest bits-per-character (1.425), improves morphological alignment (MorphScore macro-F1 0.61), and uses 19% less GPU memory than 64K-vocabulary subword tokenizers. Frozen Morpheus embeddings outperform BGE-M3 and BERTurk in lexical retrieval, with root-family MAP of 0.85 and ROC-AUC of 1.00.
SAGE is a multi-agent framework for prompt optimization that combines diagnostic code execution with quantitative validation. It improves mental-health chatbot retention by aggregating eight cycles of noisy A/B tests into statistically significant gains, demonstrating effectiveness in open-ended dialogue tasks through qualitative and quantitative feedback integration.
CAPRA is a multi-agent LLM system that generates personalized, template-compliant LaTeX feedback on software architecture deliverables. It uses specialized agents, PyMuPDF, and gpt-4o to extract and analyze text and UML diagrams, with evidence anchoring and consistency management to ensure reliability. A preliminary evaluation of 10 student reports shows CAPRA met 88.8% of eight criteria and achieved moderate inter-rater agreement (kappa = 0.582), with each report processed in under 4 minutes.
The ProductConsistency dataset introduces 87k SFT samples and 869 RL samples to improve product identity preservation in image editing. It includes a benchmark for standardized evaluation and uses a cyclic consistency reward to enforce semantic product identity through caption similarity. Fine-tuning Qwen-Image-Edit-2511 and Flux.1-Kontext-dev shows a 5x reduction in character error rate and improved text rendering and visual quality.
A new taxonomy classifies LLM agent communication protocols across five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Analysis shows hybrid payloads, session-state persistence, and runtime schema negotiation are common, with decentralized discovery remaining rare. The study predicts short-term convergence toward unified agent-to-agent and agent-to-context protocols, and long-term evolution toward a federated, layered protocol stack.
The Inflect-Nano-v1 model is the second smallest publicly released TTS model after TinyTTS, with 4.63M total parameters. It performs surprisingly well for its size, running locally on low-end devices and offering a baseline for tiny speech synthesis in embedded or offline applications.
LoopCoder-V2 is a 7B instruction-tuned code model based on Parallel Loop Transformer (PLT), trained on 18T tokens of mixed text and code data. The two-loop variant achieves the best gain-cost balance, improving SWE-bench Verified from 43.0 to 64.4, while three or more loops result in regression due to increasing positional mismatch and unstable updates.
LoopCoder-v2, a parallel loop Transformer model, achieves superior code generation and reasoning performance with two loops, improving SWE-bench Verified from 43.0 to 64.4 points and Multi-SWE from 14.0 to 31.0 points. Variants with three or more loops perform worse, indicating a non-monotonic loop-count effect due to growing positional mismatch and diminishing returns.
A multi-agent AI framework addresses premature diagnostic handoff and silent hallucinations in healthcare by enforcing structured clinical protocol completion and epistemic uncertainty quantification. Evaluations on 150 simulated cases show 49.3% diagnostic precision, an 11.3 percentage point improvement over baseline, with a statistically significant negative correlation between OLDCARTS completeness and diagnostic uncertainty.
EAGG introduces a grasp generator that aligns embodiment structure within a shared model using topology-aware graphs and geometry-aware tokens. It achieves 56.17% average grasp success on MultiGripperGrasp, matching specialized models within 1.10 percentage points and reducing median contact distance from 0.239 cm to 0.189 cm.
SwiftTrans addresses runtime efficiency gaps in LLM-based code translation by introducing Multi-Perspective Exploration and Difference-Aware Selection. The framework extends CodeNet, F2SBench, and introduces SwiftBench to evaluate runtime performance, showing consistent improvements in both correctness and efficiency across benchmarks.
CircuitLasso proposes a scalable method for learning sparse circuits in large language models using sparse linear regression. It achieves structural accuracy comparable to state-of-the-art intervention-based methods at significantly lower computational cost, while enabling efficient discovery of semantic feature propagation and improving performance on domain-generalization tasks with reduced cost.
A consensus-based agentic large language model framework is proposed for accurate 10-digit Harmonized Tariff Schedule code classification in Canadian maritime logistics. Evaluated on 3,300 expert-labeled product records, the framework shows that fine-grained HTS classification remains challenging for advanced LLMs, highlighting the need for evidence-grounded, uncertainty-aware, and human-in-the-loop workflows.
CircuitLasso enables scalable circuit learning in large language models by using sparse linear regression. It recovers circuits with structural accuracy matching state-of-the-art methods at significantly lower computational cost, and demonstrates human-interpretable semantic propagation through model components. The learned circuits achieve comparable performance on a domain-generalization task with reduced cost.