arXiv subjects

Qingchuan Li

Publications and source records attributed to Qingchuan Li.

14 recordsLinked to original sources

arXiv2026

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

cs.CL↗

arXiv2026

TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

Spreadsheets and tables are widely used representations for structured data analysis, but effective analysis still requires substantial manual effort and domain expertise. Recent large language model (LLM) agents can automate parts of this process, but they often provide limited transparency into intermediate decisions, rely on implicit assumptions, struggle with multi-table comparison, and repeat similar workflows without adapting to a user's preferences. This paper presents TabClaw, an open-source interactive AI agent for spreadsheet manipulation and table reasoning. Users upload CSV or Excel files and issue natural-language requests; TabClaw clarifies ambiguous intent, exposes an editable execution plan, streams a ReAct-style tool-using analysis loop, dispatches specialist agents for parallel multi-table reasoning, and synthesizes findings with explicit consensus and uncertainty markers. Beyond one-off analysis, TabClaw records completed workflows, extracts persistent user memory, distills reusable skills from repeated tool-use patterns, supports package-style skill import, and upgrades skills from negative feedback. Experiments on spreadsheet manipulation and table reasoning benchmarks show that TabClaw improves executable task completion and reasoning performance while preserving an inspectable user workflow. This paper shows how TabClaw turns spreadsheets and tables into inspectable analytical workflows while gradually personalizing itself to recurring data-analysis tasks. Our code is available.

cs.CL↗

arXiv2026

Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning

Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backends through two core components: a Gateway Server and a Data Pool. The Gateway Server captures multi-turn interaction steps through a unified LLM API entry point, while the Data Pool organizes them into step-level records consisting of prompt IDs, response IDs, rewards and other metadata. In our demo, users can interactively inspect live trajectories, examine the state, action, and reward of each step, curate data by quality and readiness, and configure training-ready batches for different downstream RL algorithms. Overall, Claw-R1 treats agent interaction traces as managed data assets rather than temporary runtime logs. Through this demonstration, we hope to encourage the community to recognize the importance of data management in agentic RL. Our code is available at https://github.com/AgentR1/Claw-R1 and the demonstration video can be found at link https://youtu.be/Pw47dAOw6B0.

cs.LG↗

arXiv2026

SocraticPO: Policy Optimization via Interactive Guidance

Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model should revise its mistaken reasoning, which can encourage shortcut learning and brittle policies. We propose \textbf{SocraticPO} (Socratic Policy Optimization), a policy-optimization framework that augments RL rollouts with Socratic-style natural-language guidance. During rollout, the student first answers independently; if the answer is incorrect, a teacher diagnoses the attempt and provides concise corrective guidance, after which the student continues under the expanded context. Crucially, this guidance is paired with reward decay: correct answers obtained after teacher intervention only receive decayed rewards, preventing the policy from treating teacher help as a free path to reward. Since SocraticPO only modifies the rollout process while leaving the standard expected-reward objective intact, it can be plugged into existing policy-gradient backends such as Reinforce++. Moreover, because the teacher provides only text-level guidance, SocraticPO can leverage stronger black-box teacher models without requiring access to logits or distribution matching. On undergraduate-level scientific reasoning benchmarks from SciKnowEval, SocraticPO improves over strong RL and self-distillation baselines. Ablations show that both targeted guidance and reward decay are necessary, with reward decay mitigating reliance on assisted correction.

cs.LG↗

arXiv2026

Ink Spiral: Symbolic Transformation from The Thinker to the Four Gentlemen

Western art has regarded The Thinker as a symbol of rational contemplation, while Eastern aesthetics has taken the Four Gentlemen, namely plum, orchid, bamboo, and chrysanthemum, as symbols of moral and spiritual cultivation. This paper presents Ink Spiral, a video installation that links these traditions through AI generated ink imagery. By transforming a rotating sculpture of The Thinker into the Four Gentlemen across thousands of frames, the work shifts between three dimensional sculpture and two dimensional ink, human introspection and natural symbolism. Ink Spiral turns fixed cultural icons into a fluid dialogue, inviting audiences to perceive cross cultural connection as a living, ambiguous, and endlessly interpretable creative state.

cs.HC↗

arXiv2026

COSMIC 1001: Engaging Future Speculation on Space Exploration with Generative AI

Cosmic 1001 is an interactive installation that transforms space exploration history into a speculative news experience. Participants first browse a news-based archive of major space events, then pose future-oriented questions or specify conditions such as year, celestial body, or mission name. In response, AI generates a future news item including a headline, article, narration, and visual media. These outputs are accumulated in the Future Tunnel, a shared visualization where individual stories form a collective landscape of possible futures. By combining historical space events with science fiction references, the installation explores a space between documentation and imagination, treating the future not as a fixed prediction but as a visible and discussable speculation.

cs.HC↗

arXiv2026

CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities

Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as GRPO are increasingly popular, we argue that critic-based methods remain well suited to long-horizon agentic tasks because their critic models can assess each state and assign credit to different decisions. However, representative critic-based methods such as PPO still organize value estimation, credit assignment, and policy updates at token granularity, whereas the environment state changes only after the agent completes a full action. In this work, we propose CAPO, a critic-guided action-aligned policy optimization method for advancing LLM agent capabilities. CAPO introduces two action-aligned designs. First, it estimates the state value at the action boundary using a critic model and assigns the corresponding advantage to the complete action rather than individual tokens. Second, CAPO introduces a novel action-aware policy ratio that aggregates token ratios within each action with length calibration for consistent updates across actions of different lengths. These two designs effectively achieve fine-grained credit assignment and consistent policy updates while remaining compatible with token-level gradient computation. Experiments across multi-hop QA, academic paper search, and text-world action tasks show that CAPO consistently outperforms representative RL methods. Further analyses validate both designs and reveal how action-aligned optimization improves multi-turn RL training. We hope this work provides a practical path for training more capable LLM agents.

cs.CL↗

arXiv2026

From Path Signatures to Sequential Modeling: Incremental Signature Contributions for Offline RL

Path signatures embed trajectories into tensor algebra and constitute a universal, non-parametric representation of paths; however, in the standard form, they collapse temporal structure into a single global object, which limits their suitability for decision-making problems that require step-wise reactivity. We propose the Incremental Signature Contribution (ISC) method, which decomposes truncated path signatures into a temporally ordered sequence of elements in the tensor-algebra space, corresponding to incremental contributions induced by last path increments. This reconstruction preserves the algebraic structure and expressivity of signatures, while making their internal temporal evolution explicit, enabling processing signature-based representations via sequential modeling approaches. In contrast to full signatures, ISC is inherently sensitive to instantaneous trajectory updates, which is critical for sensitive and stability-requiring control dynamics. Building on this representation, we introduce ISC-Transformer (ISCT), an offline reinforcement learning model that integrates ISC into a standard Transformer architecture without further architectural modification. We evaluate ISCT on HalfCheetah, Walker2d, Hopper, and Maze2d, including settings with delayed rewards and downgraded datasets. The results demonstrate that ISC method provides a theoretically grounded and practically effective alternative to path processing for temporally sensitive control tasks.

cs.LG↗

arXiv2026

PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization

Academic paper search is a fundamental task in scientific research, yet most existing approaches organize retrieval around predefined workflows or structured interaction protocols that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and how to invoke search and expand tools based on accumulated retrieval context. However, training such agents presents a fundamental challenge: standard reinforcement learning methods, typically designed for single-turn tasks, suffer from a granularity mismatch when applied to multi-turn agentic tasks, where token-level optimization diverges from the granularity of sequence-level interactions, leading to noisy credit assignment and unstable training dynamics. We introduce Proximal Sequence Policy Optimization (PSPO), a process-aware, sequence-level policy optimization method that aligns optimization with agent--environment interaction. Comprehensive experiments on both synthetic and real-world benchmarks demonstrate that PaperScout significantly outperforms strong structured retrieval and RL baselines in both recall and relevance, validating the effectiveness of our adaptive agentic framework and optimization strategy.

cs.AI↗

arXiv2025

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation

Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.

cs.CL↗

arXiv2025

Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning

Large language models (LLMs) have rapidly evolved from single-turn text generators into the foundation of increasingly capable agents. As these agents take on more complex reasoning, decision making, tool use, and long-horizon tasks, reinforcement learning (RL) is becoming increasingly important for shaping their behavior. This shift is especially visible in agentic RL, where models must interact with tools and environments across multiple rounds rather than produce a single standalone response. In this regime, the usual view of a trajectory as one ever-growing token sequence becomes increasingly inadequate: it makes context evolution rigid and creates representation mismatches between rollout and training. This paper presents Agent-R1, a unified and modular framework for agentic RL built around step-level trajectory representation, flexible context management, and layered interfaces for workflows, environments and optimization. The key idea is to treat each interaction step as the basic reinforcement-learning transition, while keeping the optimization layer flexible: once the interaction is modeled at the step level, the framework can support token-level credit assignment, step-level credit assignment, or other compatible designs. These design choices make the framework compatible with a range of optimization strategies rather than tying it to a single algorithm. Together, these components provide a principled, extensible, and reusable substrate for agentic RL.

cs.CL↗

arXiv2025

Tides of Memory: Digital Echoes of Netizen Remembran

This artwork presents an interdisciplinary interaction installation that visualizes collective online mourning behavior in China. By focusing on commemorative content posted on Sina Weibo following the deaths of seven prominent Chinese authors, the artwork employs data scraping, natural language processing, and 3D modeling to transform fragmented textual expressions into immersive digital monuments. Through the analysis of word frequencies, topic models, and user engagement metrics, the system constructs a semantic-visual landscape that reflects both authorial legacies and collective memory. This research contributes to the fields of digital humanities, visualization design, and digital memorial architecture by proposing a novel approach for preserving and reactivating collective memory in the digital age.

cs.HC↗

arXiv2025

Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?

Logical reasoning with large language models (LLMs) has received growing attention. One mainstream approach translates natural language into formal logic and then applies symbolic solvers for deduction. While effective in many tasks, these LLM-based translators often fail to generate consistent symbolic representations when the same concept appears in different linguistic forms. Such inconsistencies break logical coherence and lead to solver errors. However, most existing benchmarks lack this type of linguistic variation, which frequently occurs in real-world text, leaving the problem underexplored. To address this gap, we present SoLT, a benchmark that systematically rewrites reasoning datasets into diverse yet logically equivalent forms across multiple levels. Beyond evaluation, SoLT also provides a general method to enrich any dataset with linguistic diversity while preserving both meaning and logic. To further enhance the stability of LLM-based reasoning, we propose MenTaL, which explicitly guides models to build a concept-symbol mapping table during translation. By linking equivalent expressions to shared symbols, MenTaL maintains consistency and mitigates symbol drift. Experiments on SoLT demonstrate that LLMs indeed suffer from inconsistent symbol mapping under linguistic variation, leading to significant drops in reasoning accuracy. Meanwhile, applying MenTaL brings clear and stable performance improvements across diverse inputs. Overall, our findings reveal that overlooking linguistic diversity hides key weaknesses in LLM-based translators, and our work offers a step toward more reliable logical reasoning in varied real-world scenarios. Our code is available at https://github.com/wufeiwuwoshihua/LinguDiver.

cs.CL↗

arXiv2024

Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach

Large Language Models (LLMs) have exhibited remarkable potential across a wide array of reasoning tasks, including logical reasoning. Although massive efforts have been made to empower the logical reasoning ability of LLMs via external logical symbolic solvers, crucial challenges of the poor generalization ability to questions with different features and inevitable question information loss of symbolic solver-driven approaches remain unresolved. To mitigate these issues, we introduce LINA, a LLM-driven neuro-symbolic approach for faithful logical reasoning. By enabling an LLM to autonomously perform the transition from propositional logic extraction to sophisticated logical reasoning, LINA not only bolsters the resilience of the reasoning process but also eliminates the dependency on external solvers. Additionally, through its adoption of a hypothetical-deductive reasoning paradigm, LINA effectively circumvents the expansive search space challenge that plagues traditional forward reasoning methods. Empirical evaluations demonstrate that LINA substantially outperforms both established propositional logic frameworks and conventional prompting techniques across a spectrum of five logical reasoning tasks. Specifically, LINA achieves an improvement of 24.34% over LINC on the FOLIO dataset, while also surpassing prompting strategies like CoT and CoT-SC by up to 24.02%. Our code is available at https://github.com/wufeiwuwoshihua/nshy.

cs.CL↗