LLM News and AI Updates
Follow LLM developments across AI companies, labs, and open-source projects.
Latest LLM news, research, benchmarks, product releases, and industry adoption updates.
Latest Articles
- ATC: Agent Trajectory Control for Role-Contract Enforcement in Black-Box Multi-Agent Systems — Agent Trajectory Control (ATC) enforces explicit role contracts in multi-agent LLM systems by checking each message before it enters the shared conversation, reducing role drift without access to model internals.
- Planning-Coding Separation in LLM-Based Code Generation: An Empirical Study — An empirical study finds code generation works almost as well when one LLM plans and another writes code, and a large planner paired with a much smaller coder can sometimes match the large model alone.
- Thinking Fast, Trading Late: System One Decision Models vs the Market — A pre-registered test finds LLM news signals for S&P 500 stocks mostly vanish out of sample, with a fine-tuned model's information coefficient falling to 0.020 and no strategy surviving costs.
- The Evolution Strategies Paradox: Better Models from Worse Perturbations — Researchers explain why Evolution Strategies can fine-tune billion-parameter LLMs even when every perturbed offspring scores worse than the parent, tracing the paradox to noise and curvature in high dimensions.
- Treating the Symptom, Missing the Cause: Anatomy of a Scientific Reasoning Failure — In synthetic biology-style tests, seven LLM agents fixed faulty systems more often than they diagnosed them; Claude Opus 4.6 rescued every organism but identified the cause in only 55% of cases.
- ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme — ALBI swaps the symbolic hypothesis generator in inductive logic programming for an LLM checked by SWI-Prolog, and solves all 30 standard ILP benchmarks with three frontier models in 1.4-1.7 iterations on average.
- Creating Power Flexibility in Datacenters via Query Routing — A query-routing framework lets LLM datacenters cut power draw on demand without deferring requests, reaching up to 16% power flexibility in a simulated 10,000-H100 site, with 90% of the target cut landing within about 10 seconds.
- AgentAM: An AI Agent for Spatter- and Defect-Aware Process Optimization in Laser Powder Bed Fusion — AgentAM gives metal 3D-printing engineers plain-language access to CFD-trained spatter and melt-pool models through MCP, passing the right inputs in 98.5% of parsing prompts and landing within a median 1.0% of brute-force optimum.
- A Compact Formula-Aware Spreadsheet Abstraction for Large Language Models — A formula-aware abstraction compresses large spreadsheet ranges into positions, types and R1C1 formula patterns before LLMs see the data, cutting token use on a 50-query evaluation.
- EvoMemState: Evolving Memory State for Personal Agents — EvoMemState gives LLM personal agents memory that tracks how facts relate, conflict and apply to a request, using RL to build a reasoning state, and reports gains on long-term dialogue benchmarks.