arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.
arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
The paper introduces Gradient-Aligned Reward (GAR), a reinforcement learning technique that uses truncated backpropagation to generate a compact gradient vector for each rollout and compares it to an expert-anchor gradient via cosine similarity. This dense, reasoning-aware reward improves large language model chain-of-thought reasoning on math benchmarks and transfers to other tasks without domain‑specific data, while adding less than 9% computational overhead. GAR outperforms existing baselines such as GRPO on Qwen3-4B and Qwen3-8B models.
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
The paper introduces Step-wise Rubrics as Rewards (SRaR), a reinforcement learning framework that assigns rubric-based scores to individual reasoning steps in large language models. By normalizing step scores and combining them with outcome rewards through a decoupled advantage estimator, SRaR preserves criterion-level structure and mitigates issues like rewarding flawed steps or encouraging endless self‑correction. Experiments on 16K problems and six math benchmarks show that SRaR outperforms prior rubric methods, improving accuracy, increasing faithful reasoning rates, and reducing self‑correction loops.
arXiv:2605.10791v2 Announce Type: replace Abstract: Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent methods use supervision de...
Reinforcement learning (RL) has improved the capabilities of large language models (LLMs) across a wide range of tasks. However, token-level RL assigns an action's advantage to the entire generated re...
arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.
arXiv:2610.27012v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model by sampling responses, scoring them with an automatic verifier, and upd...
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
SIPO (Self‑Instructing Policy Optimization) unifies reinforcement learning with on‑policy self‑distillation by using a contrastive self‑teacher to generate token‑level credit signals. The method samples multiple rollouts per prompt, pairs each with a reference answer and its mistakes, and uses the difference in teacher log‑probabilities to provide dense feedback while still respecting the overall task reward. Experiments on reasoning and code‑generation benchmarks show that SIPO outperforms both RLVR and OPSD baselines without requiring an external teacher or extra generation steps.