Engineering
JIT-Agent: Just-in-Time Synthesis of Agent Harnesses
JIT-Agent is a harness intelligence model that generates task-adaptive agent harnesses on the fly for arbitrary off-the-shelf LLMs, formalizing the…
Engineering
D3-MOPD: Dynamic Domain Scheduling for Multi-Teacher Distillation
D3-MOPD is a zero-overhead scheduler for multi-teacher on-policy distillation that adjusts per-domain training mixture ratios online, reusing the reverse-KL signal…
Engineering
Agent-G2: Gaussian Guidance for Hint-Based Agentic Reinforcement Learning
Agent-G2 addresses reward sparsity in long-horizon agentic RL by replacing the common practice of treating expert-trajectory guidance depth as a…
Opinions
The Books Helping Readers Make Sense of the AI Moment
The Christian Science Monitor’s book critics sampled eleven nonfiction and fiction titles addressing artificial intelligence to help readers understand the…
Engineering
Code World Model: A Coding Agent as the Brain of a Video World Model
Code World Model separates world-state evolution from visual rendering by using a coding agent to reason about events and consequences…
Engineering
Is Next-Chunk Reasoning RL Really Better Than SFT on No-CoT Data?
This paper runs a controlled comparison of next-chunk reasoning reinforcement learning against a simple alternative called Mixed SFT — a…
Engineering
Open-MOPD: Closing the Capability Integration Gap in Multi-Teacher Distillation
This paper identifies a ‘capability integration gap’ in multi-teacher on-policy distillation, where a controlled benchmark shows standard methods recover only…
Engineering
SWE Refactor Bench: Testing Whether Coding Agents Can Actually Migrate Legacy Code
SWE Refactor Bench is a new benchmark of 20 whole-repository code migrations across four categories of technical debt, designed to…
Engineering
AnTrap: Benchmarking GUI Agent Robustness Against Runtime Anomalies
AnTrap is a benchmark that injects realistic dynamic anomalies — such as unexpected pop-ups and action misuse — into Android…
Engineering
The Handoff Tax: What Happens When You Switch Models Mid-Agent-Run
This study measures the cost-quality trade-off of switching between cheaper and more capable models partway through a long-running coding agent…
Engineering
Gated Recurrent Transformers: Trading Parameters for Depth via Recurrence
Gated Recurrent Transformer is a new architecture that brackets a single shared transformer core, iterated multiple times, between fixed prelude…
Engineering
Prefix Sliding: Capping Memory for Long Test-Time Reasoning
Prefix Sliding is an inference technique that discards reasoning tokens outside of a fixed prefix (containing key instructions and tools)…