15 papers
When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
Zhaohan Zhang, Junjie Liu, Chengzhengxu Li +6
The reasoning trajectory of a Large Language Model (LLM) is often treated as a verbalized description of its internal reasoning. However, such trajectories can be unfaithful: a mod…
What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory
Chen Shen
Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the resulting loss in accuracy, bu…
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Yu Feng, Chunting Zang, Chen Shen +4
Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs. We audit two widely used safety-guard…
VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
Xinyan Zhong, Yuwei Shi, Yuqi Wei +3
Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the supporting evidence within those pa…
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
Zhanming Shen, Jintao Tong, Shaotian Yan +9
On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-lev…
Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
Chen Shen
LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively attach page-level citations…
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
Bing Wang, Shaotian Yan, Chen Shen +7
Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-worl…
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
Bing Wang, Rui Miao, Ximing Li +6
The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critic…
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
Zhenliang Zhang, Wenqing Wang, Yong Hu +4
Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token c…
To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
Wei Cheng, Yongchang Cao, Chen Shen +4
Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges f…
On the Step Length Confounding in LLM Reasoning Data Selection
Bing Wang, Rui Miao, Chen Shen +7
Large reasoning models have recently demonstrated strong performance on complex tasks that require long chain-of-thought reasoning, through supervised fine-tuning on large-scale an…
ART: Attention Replacement Technique to Improve Factuality in LLMs
Ziqin Luo, Yihao Quan, Xiaofeng Zhang +2
Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrec…
Composer 2 Technical Report
Cursor Research, :, Aaron Chan +53
Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability…
Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
Kaiyuan Liu, Chen Shen, Zhanwei Zhang +3
While recent advances in large reasoning models have demonstrated remarkable performance, efficient reasoning remains critical due to the rapid growth of output length. Existing op…
GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
Zhanwei Zhang, Kaiyuan Liu, Junjie Liu +5
Local geometry-controllable computer-aided design (CAD) generation aims to modify local parts of CAD models automatically, enhancing design efficiency. It also ensures that the sha…