ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision

Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then-RL recipe creates a different supervision misalignment at each stage. SFT is expected to teach how to use tools, but trajectories from stronger teachers may succeed through perceptual capabilities that a smaller student cannot reliably reproduce or exploit, causing the student to imitate tool-call patterns without learning how to make them useful. RL is expected to teach when to use tools, but outcome-only rewards make fallible tool execution a liability and suppress tool use, whereas a blanket bonus for every correct tool-using trajectory encourages valid but ineffective operations. To address these two misalignments, we introduce ToolVision. During SFT, a multi-agent pipeline explores candidate trajectories, and a committee including student-scale models scores stepwise evidence gain to rank and prune the search branches. Only successfully executed trajectories with correct final answers are retained for SFT. Before RL, ToolVision compares the learner's performance with and without tools, then rewards successful tool use only on questions where tools provide a clear benefit. Both signals are constructed automatically from public task data without additional human annotations of tool use or necessity. ToolVision-8B improves over its base on all seven main benchmarks, surpasses Thyme-7B, CodeVision-8B, and CodeDance-7B on all three high-resolution benchmarks, and outperforms Qwen3-VL-32B-Thinking on V* and HRBench 8K. We will publicly release the datasets and source code.

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads to representation mismatch, where relevant information is available but not organized for the current decision. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and render transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the effect of such staleness in asynchronous GRPO. We make the behavior policy explicit in the GRPO surrogate objective and distinguish between the surrogate-gradient mapping used by the learner and the true total derivative of a distribution-dependent population objective. Under assumptions of local boundedness, distributional smoothness, and behavior-policy smoothness, we show that stale rollouts introduce a per-step surrogate-gradient bias of order O(S * eta), where S denotes the maximum rollout lag and eta denotes the learning rate. We further derive a conditional collapse-time scaling law: when within-cycle drift remains below a batch-level clipping radius, collapse is governed primarily by cumulative learner drift T * eta; when the stale-rollout constraint is active, stability instead depends explicitly on S * eta. This yields a two-constraint stability condition eta << min{R_batch / (S * G_upd), R_crit / (T * G_upd)}, explaining why the maximum stable learning rate may appear weakly dependent on staleness in the horizon-limited regime.

PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents

Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet give limited account of how accumulated interaction evidence is abstracted into person understanding. We view this process as schema formation, where situated evidence is abstracted into reusable patterns and stable person level claims. We introduce PersonaTree, a structured lifecycle memory framework that realizes this view as a three level persona tree with explicit support paths from evidence to claims. PersonaTree maintains the tree through conservative writing, confidence guided consolidation, and query conditioned path retrieval, returning only the evidence depth required by each query. Across six person understanding and persistent memory benchmarks with three answer backbones, PersonaTree ranks first in 12 of 18 compact scores and reaches the top two in 16 settings. Ablations show that hierarchy improves abstract person understanding on KnowMe, while support path retrieval improves RealPref alignment under a comparable context budget.

Co-Evolution of Policy and Internal Reward for Language Agents

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit assignment or external reward models, which provide limited guidance at inference time and often separate reward improvement from policy improvement. We propose Self-Guide, a self-generated internal reward for language agents that supports both inference-time guidance and training-time supervision. Specifically, the agent uses Self-Guide as a short self-guidance signal to steer the next action during inference, and converts the same signal into step-level internal reward for denser policy optimization during training. This creates a co-evolving loop: better policy produces better guidance, and better guidance further improves policy as internal reward. Across three agent benchmarks, inference-time self-guidance already yields clear gains, while jointly evolving policy and internal reward with GRPO brings further improvements (8\%) over baselines trained solely with environment reward. Overall, our results suggest that language agents can improve not only by collecting more experience, but also by learning to generate and refine their own internal reward during acting and learning.

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the verification mechanism itself remains largely unchanged, relying on strict token-level rejection sampling. In practice, modern LLMs frequently operate in low-margin regimes where the target model exhibits weak preference among top candidates. In such cases, rejecting plausible runner-up tokens yields negligible information gain while incurring substantial rollback cost, leading to a fundamental inefficiency in verification. We propose Margin-Aware Speculative Verification, a training-free and domain-agnostic verification strategy that adapts to the target model's local decisiveness. Our method conditions verification on decision stability measured directly from the target logits and relaxes rejection only when strict verification provides minimal benefit. Importantly, the approach modifies only the verification rule and is fully compatible with existing target-coupled speculative decoding frameworks. Extensive experiments across model scales ranging from 8B to 235B demonstrate that our method delivers consistent and significant inference speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks.

Teaching Large Reasoning Models Effective Reflection

Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are superficial, offering little to no improvement over the original answer and incurring computation overhead. In this paper, we identify and address the problem of superficial reflection in LRMs. We first propose Self-Critique Fine-Tuning (SCFT), a training framework that enhances the model's reflective reasoning ability using only self-generated critiques. SCFT prompts models to critique their own outputs, filters high-quality critiques through rejection sampling, and fine-tunes the model using a critique-based objective. Building on this strong foundation, we further introduce Reinforcement Learning with Effective Reflection Rewards (RLERR). RLERR leverages the high-quality reflections initialized by SCFT to construct reward signals, guiding the model to internalize the self-correction process via reinforcement learning. Experiments on two challenging benchmarks, AIME2024 and AIME2025, show that SCFT and RLERR significantly improve both reasoning accuracy and reflection quality, outperforming state-of-the-art baselines. All data and codes are available at https://github.com/wanghanbinpanda/SCFT.

Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning

Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing training recipes implicitly bias models toward a limited set of dominant patterns. Through a systematic analysis, we identify substantial accuracy variance across these patterns on mathematics and science benchmarks, revealing that a model's default reasoning pattern is often sub-optimal for a given problem. To address this, we introduce Group Pattern Selection Optimization (GPSO), a reinforcement learning framework that extends GRPO by incorporating multi-pattern rollouts, verifier-guided optimal pattern selection per problem, and attention masking during optimization to prevent the leakage of explicit pattern suffixes into the learned policy. By exploring a portfolio of diverse reasoning strategies and optimizing the policy on the most effective ones, GPSO enables the model to internalize the mapping from problem characteristics to optimal reasoning patterns. Extensive experiments demonstrate that GPSO delivers consistent and substantial performance gains across various model backbones and benchmarks, effectively mitigating pattern sub-optimality and fostering more robust, adaptable reasoning. All data and codes are available at https://github.com/wanghanbinpanda/GPSO.

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in decentralized settings, where network latency often dominates compute, remains under-characterized. We present Decentralized Speculative Decoding (DSD), a plug-and-play framework for decentralized inference that turns communication delay into useful computation by verifying multiple candidate tokens in parallel across distributed nodes. We further introduce an adaptive speculative verification strategy that adjusts acceptance thresholds by token-level semantic importance, delivering an additional 15% to 20% end-to-end speedup without retraining. In theory, DSD reduces cross-node communication cost by approximately (N-1)t1(k-1)/k, where t1 is per-link latency and k is the average number of tokens accepted per round. In practice, DSD achieves up to 2.56x speedup on HumanEval and 2.59x on GSM8K, surpassing the Eagle3 baseline while preserving accuracy. These results show that adapting speculative decoding for decentralized execution provides a system-level optimization that converts network stalls into throughput, enabling faster distributed LLM inference with no model retraining or architectural changes.

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities

This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It challenges MLLMs to generate a correct program that fulfills specific functionality requirements based on a given flowchart, which visually represents the desired algorithm or process. Code-Vision comprises three subsets: HumanEval-V, Algorithm, and MATH, which evaluate MLLMs' coding abilities across basic programming, algorithmic, and mathematical problem-solving domains. Our experiments evaluate 12 MLLMs on Code-Vision. Experimental results demonstrate that there is a large performance difference between proprietary and open-source models. On Hard problems, GPT-4o can achieve 79.3% pass@1, but the best open-source model only achieves 15%. Further experiments reveal that Code-Vision can pose unique challenges compared to other multimodal reasoning benchmarks MMCode and MathVista. We also explore the reason for the poor performance of the open-source models. All data and codes are available at https://github.com/wanghanbinpanda/CodeVision.