Cover Image

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sui, Yuan, Chen, Yulin, Li, Yibo, Jiang, Xue, He, Yufei, Dong, Yihong, He, Xiaoxin, Gao, Tianyu, Hooi, Bryan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
by: He, Yufei, et al.
Published: (2024)

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
by: Sui, Yuan, et al.
Published: (2024)

UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
by: He, Yufei, et al.
Published: (2025)

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
by: He, Yufei, et al.
Published: (2025)

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
by: Sui, Yuan, et al.
Published: (2025)

Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering
by: Sui, Yuan, et al.
Published: (2024)

EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
by: He, Yufei, et al.
Published: (2026)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
by: Li, Yibo, et al.
Published: (2026)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
by: Chen, Yulin, et al.
Published: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
by: Yang, Xianglin, et al.
Published: (2026)

Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation
by: Sui, Yuan, et al.
Published: (2026)

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
by: He, Yufei, et al.
Published: (2025)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
by: Chen, Yulin, et al.
Published: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
by: Chen, Yulin, et al.
Published: (2026)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification
by: Hu, Jun, et al.
Published: (2025)

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
by: Cao, Tri, et al.
Published: (2026)

Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning
by: Hu, Jun, et al.
Published: (2025)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
by: Chen, Yulin, et al.
Published: (2025)

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
by: Li, Yibo, et al.
Published: (2026)

FlowReasoner: Reinforcing Query-Level Meta-Agents
by: Gao, Hongcheng, et al.
Published: (2025)

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
by: Deng, Ailin, et al.
Published: (2024)

Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion
by: Li, Yuan, et al.
Published: (2026)

Enhancing Multi-Agent Debate System Performance via Confidence Expression
by: Lin, Zijie, et al.
Published: (2025)

Efficient Heterogeneous Graph Learning via Random Projection
by: Hu, Jun, et al.
Published: (2023)

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
by: Lou, Zhanzhi, et al.
Published: (2026)

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
by: Chen, Hui, et al.
Published: (2025)

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
by: Li, Yuexin, et al.
Published: (2026)

Self-collaboration Code Generation via ChatGPT
by: Dong, Yihong, et al.
Published: (2023)

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
by: He, Xiaoxin, et al.
Published: (2023)

FlipAttack: Jailbreak LLMs via Flipping
by: Liu, Yue, et al.
Published: (2024)

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
by: He, Yufei, et al.
Published: (2025)

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
by: Yin, Jianghao, et al.
Published: (2026)

Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training
by: He, Yufei, et al.
Published: (2024)

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
by: Bin, Yi, et al.
Published: (2025)

DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs
by: Li, Yuan, et al.
Published: (2025)

Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection
by: Li, Yuan, et al.
Published: (2026)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
by: Li, Yibo, et al.
Published: (2025)

Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
by: Guo, Qianyun, et al.
Published: (2026)