Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #10911

PPO

Related event timeline, sources and context from the news index.

EVENT TIMELINE

4

RESEARCH · 1 SOURCE · Apple Machine Learning Research

Theoretical Limits of Language Model Alignment

The paper derives information-theoretic limits on reward improvement under a fixed KL-divergence budget for KL-regularized alignment, giving a closed-form expression governed by a Jeffreys divergence term and a reformulation as a covariance under the base model that yields a practical estimator. It also shows the proxy-reward (reward hacking) gap grows with reward error and lower KL penalties, proves reward ensembling reduces reward hacking, and empirically finds best-of-N nearly reaches the theoretical KL–reward Pareto frontier while PPO and GRPO remain substantially suboptimal on safety and summarization tasks.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Evidence-driven multi-agent AI (DRL + LLM) for head & neck proton PBS radiotherapy planning (arXiv:2610.29010v1)

This arXiv preprint proposes a compound AI system that combines a PPO-trained policy network to generate multiple proton PBS treatment plans with an LLM-based multi-agent conversational refinement layer. The planning agent (based on Qwen3-14B and post-trained with SFT and GRPO), a chatbot interface, and an evaluation agent were tested on 21 head-and-neck cancer patients (5 PPO plans each; 50 plans selected for instruction-guided refinement), and the post-trained Qwen3-14B improved instruction-following, retrieval and domain reasoning to produce clinically more appropriate trade-offs during user-guided plan adjustments.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker AI demonstrates multi-turn reinforcement learning (MTRL) fine-tuning for search agents with Qwen3.6-27B

Amazon’s blog post describes using Amazon SageMaker AI’s multi-turn reinforcement learning (MTRL) capability to fine-tune a Qwen3.6-27B model for an LLM-powered search agent. The write-up details MTRL features—serverless execution, modular agent-environment interfaces, asynchronous rollouts, built-in algorithms (PPO, CISPO, IS), trajectory observability via MLflow, and evaluation jobs—and shows an enterprise search use case combining BM25 and vector search tools.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Mechanistic audit of self-discovered RL rule Disco103 shows when learning history helps or hinders

arXiv:2609.35897v1 presents the first causal mechanistic audit of a self-discovered reinforcement-learning update rule (Disco103). By surgically pinning, freezing, and transplanting recurrent states while holding meta-parameters fixed, the paper reports three findings: recurrent history expands usable reward scales (a six‑decade window vs three under zero‑pinning), mismatched history penalties stem from perpetual clamping mitigated if imported state is allowed to evolve, and controlling replay retention can reverse apparent adaptation advantages over DQN under environmental change; results are validated against a second rule (OPEN).

7.0