arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.
arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.
CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.
arXiv:2607. 02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs.
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
arXiv:2608. 03972v1 Announce Type: new Abstract: On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models.
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples.
arXiv:2607. 19345v1 Announce Type: cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier.
The paper introduces Highlight-Then-Summarize (H2S), a two-step approach that first highlights question-relevant evidence in long documents and then condenses it into a compact, question-conditioned summary before generating an answer. The authors built the H2S-Dataset with 6,647 examples spanning 11 benchmark families, and developed H2S-RL to reward evidence selection and summary construction. Evaluated on the H2S-Bench suite, the H2S-14B model outperforms larger open-source models, achieving the highest overall score and maintaining strong performance even with a reduced output budget.
StateTree is a reinforcement learning approach that improves long‑term dialogue reasoning by building a tree‑structured auxiliary task from limited dialogue data. The method embeds key‑value records across multiple sessions into a binary tree, requiring the model to traverse from root to leaf, retrieve records, compare timestamps, and identify a target question among distractors. Curriculum RL training increases tree depth, and a compositional variant trains the model to combine partial reasoning fragments, enabling cross‑session retrieval, temporal reasoning, knowledge updates, and multi‑hop reasoning while generalizing from 10K‑token to 128K‑token contexts.
arXiv:2508. 10123v3 Announce Type: replace-cross Abstract: Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT).
arXiv:2607. 02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information.
arXiv:2608.30426v1 Announce Type: new Abstract: Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by a...