arXiv:2604. 01413v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions.
arXiv:2604. 05164v3 Announce Type: replace-cross Abstract: As LLM reasoning performance plateaus, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries.
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
arXiv:2606. 18910v1 Announce Type: new Abstract: Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning.
The paper introduces Conformalized Agentic Search (CAS), a framework that applies Conformal Prediction to improve the reliability of search agents during reinforcement learning fine-tuning. CAS uses an Adaptive Prediction Set (APS) to dynamically truncate retrieved documents based on statistical coverage, and Adaptive Conformal Inference (ACI) to construct confidence-aware prediction sets that penalize low‑confidence trajectories in the Group Relative Policy Optimization objective. Experiments on single‑hop and multi‑hop QA datasets show that CAS enhances reasoning accuracy and reduces redundant tool invocations, offering a more reliable and efficient agent paradigm.
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
arXiv:2607. 10966v1 Announce Type: new Abstract: We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning.
arXiv:2604. 04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking.
arXiv:2606. 27009v1 Announce Type: new Abstract: Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations).
WordPolo is a word‑finding task that evaluates language models by having them guess an unknown target word and receive semantic similarity feedback. Participants start with no knowledge, make iterative guesses, and receive distance scores that guide them through semantic space. The study tests recent LLMs, LRMs, humans, and a heuristic on 1,500 puzzles, revealing that while solve rates vary widely, many models make meaningful progress and exhibit human‑like strategies, highlighting the importance of assessing reasoning processes, not just final accuracy.
arXiv:2604. 20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks.
arXiv:2607. 13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
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...