Engineering
Using Grounded Theory for Agent Behavior Analysis at Scale
Researchers adapt grounded theory, a decades-old qualitative research method from the social sciences, into AutoTraceGT, the first automated multi-agent pipeline…
Engineering
Environment Evolution for Terminal Agents
A new paper proposes environment evolution, a method that incrementally increases the difficulty of training environments for terminal agents off-policy…
Engineering
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
NeoMME introduces a family of compact 260M and 800M-parameter bidirectional encoders that process multilingual text and raw image patches within…
Engineering
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
This work challenges the assumption that recurrent linear-attention layers require higher precision than other model components, showing that the Gated…
Engineering
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This paper addresses the memory bottleneck created by large key-value caches during extended LLM reasoning by proposing Random Attention, which…
Engineering
Hardware-Aware FP4 FlashAttention-4
This work tackles a performance bottleneck in attention computation on Blackwell GPUs’ 4-bit floating-point tensor cores, where softmax conversion and…
Engineering
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
This paper addresses the difficulty of assigning credit across long, multi-step agent trajectories during reinforcement learning, where sparse end-of-episode rewards…
Engineering
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
This paper addresses the scarcity of executable environments needed to train terminal-based coding agents by reconstructing usable environments directly from…
Engineering
LatentPress: Context Compression Beyond Text and Vision
This paper addresses the inefficiency of storing and processing long conversational histories and documents by introducing a machine-facing compression interface…
Engineering
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
This paper investigates on-policy distillation (OPD) by studying what happens when training uses minimal data, down to a single query,…
Engineering
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
This paper addresses the slow, strictly sequential token generation inherent to autoregressive language models by introducing diffusion-augmented LLMs that define…
Engineering
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
This paper addresses text-transformation tasks that are conceptually simple to describe but hard to implement with traditional rule-based code, while…