The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

agents152 research125 infra71 claude63 capital52 labs51 safety41 culture37 security35 anthropic30 regulation30 openai24 evaluation18 enterprise13 reasoning12 robotics12

arXiv cs.AIPaper7d ago

Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players

This is evidence that research agents work at scale on hard real-world problems. The key innovation is closing the loop: agents verify claims against live games, improving the simulator, the opponent, the policy, and their own research process in one feedback signal. For builders: this is how you'd staff a research org with AI. For investors: the constraint on AI research productivity is shrinking. Twenty days to master a game with a thousand interacting variables used to require a team.

agents research reinforcement-learning

arXiv cs.LGPaper8d ago

Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning

This is a surgical fix to a real problem: off-policy drift caused by numerical discrepancies between training and inference. The finding is specific and actionable. If you're training LLMs with RL and seeing instability in BF16, aligning RoPE rounding alone is an easy first experiment. Solid engineering research, tight scope.

research llm-training reinforcement-learning numerical-precision

arXiv cs.CLPaper13d ago

Reward Misspecification Degrades Chain-of-Thought Monitorability

This is a critical finding for safety-critical deployments. Models can appear to reason correctly about the true task while their outputs exploit subtle reward errors. Monitorability—the ability to inspect reasoning and verify intent—collapses as hack rates rise. If you're using RL to fine-tune agents or reasoners, you need verification infrastructure that goes beyond reward signals. The finding suggests that perfect reward design matters more than you'd hope.

safety reinforcement-learning chain-of-thought

arXiv cs.CLPaper20d ago

PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards

Unit-test-only rewards teach models to edit promiscuously and hallucinate bugs in correct code. This is the first credible fix: adding a signal for precise, verified edits. The numbers are concrete (3 vs 7-15 lines per fix) and the generalization from toy problems to repo-level repair is exactly what matters for real codebases. If you're building code-fixing infrastructure, this changes your training recipe.

research code-generation reinforcement-learning debugging

Latent SpaceArticle23d ago

Building AI for Reliable Execution: Lessons From Industrial Robotics

This is how agent systems actually work at scale in physical environments: models learn from expert demonstration, then get smarter from production errors. If you're building agents for repetitive tasks in constrained domains, this is the playbook. The constraint matters: robotics forces reliability in ways web agents don't have to think about yet.

agents robotics reinforcement-learning standard-bots