ai-models - The LGTM (Page 5)

The LGTM

Sign in Subscribe

ai-models

A collection of 177 posts

On-Policy Distillation Looks Dense on Paper, but the Parameter Updates Are Sparse Where It Counts

On-Policy Distillation Looks Dense on Paper, but the Parameter Updates Are Sparse Where It Counts

On-policy distillation sounds like it should rewrite models broadly. The student generates its own trajectories, the teacher provides dense token-level feedback, and the optimizer gets a lot more signal than sparse reward RL. The surprise in this paper is that the final parameter updates still look selective. “Dense Supervision, Sparse

EvoArena Shows Why Agent Memory Needs Git-Style History, Not Just a Bigger Scratchpad

EvoArena Shows Why Agent Memory Needs Git-Style History, Not Just a Bigger Scratchpad

Agent memory keeps getting described as a bigger notebook. EvoArena makes the better argument: it should look more like git history. The benchmark suite evaluates agents in environments that change over time: terminal workflows, software repositories, and user preferences. Its paired method, EvoMem, wraps ordinary memory systems with append-only patch

RA-RFT Says Retrieval for Reasoning Should Find Analogies, Not Keyword Neighbors

RA-RFT Says Retrieval for Reasoning Should Find Analogies, Not Keyword Neighbors

Retrieval-augmented generation has a bad habit: it assumes the useful thing is the thing with the most similar words. RA-RFT is a reminder that reasoning does not work that way. The paper, from researchers affiliated with Meta Superintelligence Labs and Rice University, proposes Retrieval-Augmented Reinforcement Fine-Tuning: a post-training method that

DIRECT Says Bigger VLM Planners Are Often Just Slower. Route the Robot's Brain Instead

Robots make the agent-cost problem impossible to ignore. A browser agent can waste twenty seconds “thinking” and merely irritate you. A robot arm doing the same thing is just standing there, burning latency in the physical world while a banana waits for a frontier model to discover object permanence. That

APPO Moves Agent Training Past Tool Calls: The Important Decisions Are Hiding Inside the Reasoning Trace

APPO Moves Agent Training Past Tool Calls: The Important Decisions Are Hiding Inside the Reasoning Trace

APPO starts from a simple accusation against the current agent-training playbook: tool calls are convenient boundaries, not necessarily the moments where the agent made the important decision. Anyone who has reviewed a bad coding-agent trace has seen this movie. The command that failed is visible. The mistake happened three paragraphs