Skip to content
All tags

#reasoning

17 posts

Multi-hop Retrieval: When Answers Are Scattered Across Documents

Standard RAG retrieves one set of documents per query, but real questions often need reasoning across 2-4 documents. IRCoT pioneered interleaved retrieval-reasoning, PAR²-RAG beats IRCoT by 23.5% accuracy on four benchmarks, and CompactRAG compresses LLM calls down to just two.

Agentic / Reasoning RAG: From Search-R1's RL Multi-Turn Search to Deep Research and MCP's Reasoning × Retrieval Paradigm

In 2025 RAG stopped being 'retrieve once, generate once.' Search-R1 trains models to search autonomously in multiple turns with RL, REX-RAG/AlignRAG add policy and alignment branches, OpenAI Deep Research productizes the loop, and MCP generalizes retrieval into unified tool invocation. This post unpacks the design philosophy, trade-offs against ten generations, and when to adopt the new paradigm.

2025 AI Conference Review: Machine Learning

ML conferences broke every submission record in 2025 and pushed peer review to its limit. NeurIPS received 21,575 papers and used more than 20,000 reviewers; ICML passed 12,000 for the first time, and ICLR reached 11,565. Reasoning and agents were the strongest trends. One NeurIPS runner-up, the conference's only perfect-score paper, challenged whether RLVR creates new reasoning ability. Awards for Alibaba Qwen's Gated Attention and a mechanistic theory of neural scaling laws showed a community moving from scaling at all costs toward understanding why scaling works.

What Top AI Conferences Accepted in 2025: The Agent Breakout and Reasoning Revolution

The two strongest signals at AI conferences in 2025 were reasoning papers jumping from 47 to 216, a 4.6-fold rise, and agent-related terms exceeding 150 papers with 4.3–11-fold growth. Diffusion moved from breakout topic to infrastructure; RAG became a mainstream enterprise architecture with unusual coverage across all five conferences; state-space models and world models began tracing the early 2020–2021 path of Vision Transformers. Pure prompt-engineering papers encountered reviewer fatigue.

Gemini——Google's Native Multimodal Flagship: 1M Context and Scientific Reasoning Champion

Gemini is Google DeepMind's native multimodal LLM family, famed for a 1M-token context window and native video/speech input plus scientific reasoning. 3.1 Pro tops GPQA Diamond 94.1% and ARC-AGI-2 77.1% to claim science-reasoning dual crowns, at $2/$12—1/6 of Claude. 3.7 Flash delivers near-Pro agent capability for $0.75/$3.75.

GPT——Closed API for Revenue, Open GPT-OSS for Ecosystem: the Unified Routing Platform Behind the World's Largest AI Service

GPT is OpenAI's LLM family, from 117M parameters in 2018 to the three-tier GPT-5.6 Sol/Terra/Luna lineup in 2026, serving 1B+ users and 2M enterprise customers. GPT-5.6 Sol leads LiveBench 81.1%, Terminal-Bench 2.1 88.8%, and Artificial Analysis Coding Agent Index 80 across multiple agentic benchmarks, while OpenAI's first open-weight model GPT-OSS ships under Apache 2.0.

Kimi——From a 200K Long-Context Tool to a 2.8T Open-Source Frontier, and K3's Architectural Leap

Kimi is Moonshot AI's LLM family, born from ultra-long context. Kimi K3 (2026/07) is the world's first open 3T-class model—2.8T params, 104B active, 1M context, scoring 60 on the Artificial Analysis Intelligence Index tied with GLM-5.3 for open-source #1. Its Kimi Delta Attention brings a 2.5× scaling efficiency gain.

CS224N Lecture 19: How Small Models Can Move Beyond Brute-Force Scaling

The final lecture frames Open Questions in NLP 2026 as smart scaling: prolonged RL, Prismatic synthetic data, RL as pretraining, and open collaboration seek reasoning gains beyond adding parameters.

CS224N Lecture 12: Decoding, DeepSeek-R1, and Reasoning Training

Lecture 12 shows that output policy is not a detail: greedy, beam, and sampling produce different text. It then moves from R1-Zero/R1 into PPO, GRPO, and DAPO, asking when longer reasoning actually helps.

CS224N Lecture 13: Speculative Decoding and Test-Time Scaling

Lecture 13 moves from inference efficiency to inference capability: speculative decoding drafts with a small model and verifies with a large one; on-policy distillation addresses drift; long context and test-time scaling spend inference resources.

CS336 Lecture 16: RLVR Scales Reasoning with Verifiable Rewards, but GRPO Is Not Free PPO

Lecture 16 moves from PPO to GRPO and RLVR. Math, code, and environment outcomes provide scalable rewards and avoid some preference-model overoptimization, but group-normalized advantages introduce difficulty and length bias while rollout infrastructure becomes the dominant cost.

Berkeley CS288 Part 5: Inference-time Compute, Reasoning, and Embodied Agents

Units 15–18 place NLP models inside perception, reasoning, tool, and environment loops; the question shifts from next-token prediction to allocating inference compute and validating multi-step action.

Stanford CS329A: A Course on Self-Improvement That Says Out Loud What It Can't Improve

CS329A is built around the generation–verification gap: models can produce the right answer but can't tell which one it is. The conclusion the course draws about itself matters more — today's methods make models more consistent, not smarter. Nine lectures are public, out of twenty.

ai deep-dive

Resource Rationality for Agents: Optimal Decisions Across Tokens, Tool Calls, and Latency

Agent decision-making under resource constraints is bounded rationality reborn: Rational Metareasoning uses VOC rewards to save 20-37% of tokens, BATS proves that adding budget without budget awareness is futile, FrugalGPT cascades cut costs by up to 98%, and Speculative Actions reduce latency by 20%. The three constraints ultimately converge into a single Pareto curve, and the overarching trend is moving from humans tuning knobs to models making resource-rational decisions on their own.

ai deep-dive

Machine Theory of Mind: How Agents Infer Other Agents' Intentions, Knowledge, and Goals

Inferring another's beliefs/goals/intentions from observed behavior is called Machine Theory of Mind. Three lineages: symbolic BDI, Bayesian inverse planning, and deep learning ToMnet. The biggest controversy in the LLM era is that GPT-4 still trails humans by >10 points on ToMBench — are high scores genuine reasoning or statistical shortcuts?

ai guide

The Three Core Pillars of AI Agents: Context, Cognition, Action

An AI agent is not a black box — it is built from three layers: what it knows (Context), how it thinks (Cognition), and what it can do (Action). Understanding these three layers is the key to grasping why agents are sometimes brilliant and sometimes go off the rails, and how to design a truly effective agent system.

Plan-and-Execute: A RAG Pattern That Plans Before It Acts

For complex queries, have the LLM map out what information is needed and in how many steps — then execute that plan. More systematic than thinking on the fly.