MemHarness: Memory Is Reconstructed, Not Replayed
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to…
Latest
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However,…
OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation
Open-vocabulary Earth observation (EO) aims to localize geospatial concepts specified in natural language rather than a fixed label set. Existing benchmarks, however, usually cover narrow category…
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as…
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from…
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they typically decouple the initialization and DMD stages -- which then…
Voice Memory for Agentic Speech Recognition
We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory.md and decides per utterance…
πR^2: Reactive Real-time Flow Policies
Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones. Such chunks run open-loop, so the policy cannot react to…
Memory for Large Language Models
Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an implicit byproduct of computation to a spectrum of explicit, controllable…
CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation
On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student…