Engineering
TTPO: Test-Time Policy Optimization for Label-Free Reasoning
Researchers propose Test-Time Policy Optimization (TTPO), a label-free training objective for adapting language models to math reasoning tasks at test…
Engineering
Training Agents to Evolve with Their Harness: The TaoLive Digital Avatar System
A technical report from Alibaba’s Taobao Live team describes Harness-Aware Training (HAT), a method for training compact models to adapt…
Engineering
PILOT: A Supervisor-Worker Harness for Live Agent Self-Improvement
This paper introduces PILOT, a supervisor-worker agent harness that performs self-improvement live during a run rather than only after it…
Engineering
Understanding Evolution Strategies for LLM Reasoning: Broader Coverage Than GRPO
This study systematically compares Evolution Strategies (ES) against Group Relative Policy Optimization (GRPO) as post-training paradigms for LLM reasoning. It…
Engineering
WikiSkill: Co-Evolving Agent Skills with a Persistent Knowledge Base
WikiSkill is a framework that co-evolves an LLM agent’s reusable skill library alongside a persistent wiki-style knowledge base, separating raw…
Engineering
CaSKG: Counterfactual-Causal Skill Graphs for Agent Skill Retrieval
CaSKG is a retrieval framework that calibrates the reliability of a skill graph’s edges before using it to retrieve procedural…
Engineering
What Does an Evaluation License? A Reproducibility Audit of Inspect Evals
This paper formalizes what is required to legitimately ‘replay’ a claim attached to an LLM evaluation metric, then applies that…
Engineering
VoiceMem: Streaming Dual-Brain Memory for Real-Time Speech Agents
VoiceMem is a memory architecture for duplex speech language models built around a parallel ‘informational left brain’ and ’emotional right…
Opinions
The Augmentation-Automation Race: Why Today’s AI Policy Choices Decide Tomorrow’s Jobs
Anton Leicht argues that policymakers face a consequential choice between two futures for AI and labor: augmentation, where AI enhances…
Opinions
Why the Global South Will Have More AI Leverage Than Ever
Saxon Zvina argues that developing nations in the Global South hold unprecedented strategic leverage in shaping the future of artificial…
Engineering
FrontierChallenge: A Benchmark for End-to-End Scientific Agent Workflows
FrontierChallenge is a new cross-domain benchmark of 300 end-to-end scientific workflows spanning quantum chemistry, molecular dynamics, materials science, and other…
Engineering
WarpSAC: Regime-Aware Off-Policy Reinforcement Learning for Massively Parallel Simulation
This paper shows that common off-policy RL stabilizers behave differently depending on data regime: parameter normalization helps under narrow replay…