AI Funding: Latest AI News and Analysis
Read latest AI Funding coverage, including top stories, analysis, and source links.
Track AI Funding updates with focus on product moves, market signals, and high-impact developments.
Latest Articles
- 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.
- IntentGEO: Intent-aware Generative Engine Optimization for Recommendation — IntentGEO shows that generative engine optimization gains depend on user intent, and its Anchored Meta-Optimization method raised average citation-rank gain by 35% over the best prior learning-based baseline, including on the commercial assistant Doubao.
- ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement — ReSI-Math recovers math problems a model fails directly by searching its own reasoning trajectories, then uses them for data-efficient RLVR, lifting Qwen3-VL-8B's MATH500/WE-MATH average from 78.71 to 80.16.
- WASP-Mem: Let Agent Organize Procedural Memory. Human Spend Effort on Diagnosis — WASP-Mem has agents distill execution traces into linked wiki pages as procedural memory, raising TheAgentCompany checkpoint pass rates by 4.6–6.1% over the best baseline with 57–61% less storage.
- CORA: Teacher-Guided Causal O-RAN Adaptation for Jamming Detection — CORA uses a retrospective teacher detector to train a causal, label-free jamming detector for 5G O-RAN, raising mean recall from 0.687 to 0.771 across ten testbed configurations.
- AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance — AlgoPilot trains small models to pick a solving paradigm and structure the problem before execution, lifting Qwen3-8B's average accuracy from 38.4% to 72.9% across 13 benchmarks and beating GLM-5 prompting by 11.7 points.
- TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions — TactiNavi, the serving system behind the LLM coach in a commercial open-world game, makes strategy prerequisites explicit and lifts correctness on logged coaching turns from 57.9% to 82.0%, while showing most apparent fixes were just generation noise.
- Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning — WebCatalyst trains models to generate interactive HTML by playing their own outputs in a browser, lifting Qwen3.6-35B-A3B on Cookie-Bench Mini Games from 68.8 to 75.3 and ahead of Claude Opus 4.7 in average rank.
- Adversarial Speculative Reasoning Improves Long Horizon Agents — Speculative decoding is not neutral for long-horizon agents: numerical noise shifts reasoning after about 30 steps, and training the draft model to be rejected at critical decision points raises agentic coding success without changing the target model.
- PianoBench: Evaluating Musical Perception and Reasoning in Language Models — PianoBench shows open-weight audio-language models top out at 52.8% on musical reasoning from audio, while frontier models reach 93.2% when given music as text transcripts, exposing a perception gap.