AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.
Canonical reference
Tree of thoughts: Deliberate problem solving with large language models.Advances in neural information processing systems, 36:11809–11822
Canonical reference. 100% of citing Pith papers cite this work as background.
8
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
years
2026 8polarities
background 5representative citing papers
LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
PGR expands user queries into plausible future steps via Tree-of-Thought or chains and uses them as retrieval probes, delivering nearly 3x recall gains on the new MemoryQuest benchmark for low-similarity memory retrieval.
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
A persona-driven multi-agent framework with a three-dimensional decision-theoretic evaluation shows that agent-persona alignment significantly impacts performance and coordination in O-RAN optimization challenges.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
Reasoning-token augmentation dominates architectural bias for state-based recall tasks; hybrid advantages are narrow and task-dependent rather than uniform.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
citing papers explorer
-
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.
-
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
-
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
PGR expands user queries into plausible future steps via Tree-of-Thought or chains and uses them as retrieval probes, delivering nearly 3x recall gains on the new MemoryQuest benchmark for low-similarity memory retrieval.
-
State-Centric Decision Process
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
-
Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN
A persona-driven multi-agent framework with a three-dimensional decision-theoretic evaluation shows that agent-persona alignment significantly impacts performance and coordination in O-RAN optimization challenges.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
-
Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
Reasoning-token augmentation dominates architectural bias for state-based recall tasks; hybrid advantages are narrow and task-dependent rather than uniform.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.